Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to legal processes, restrictions, or violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by suffixes (-ating, -ize, -tion, -amos, etc.)

    np_acts-logits-general · gemini-2.0-flash

    assign, invalidate, select, scrutinize, associate, demonstrate, modify, recognize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.58
    <eos>
    -0.57
    argli
    -0.57
    DataSnapshot
    -0.56
    في
    -0.55
    tetten
    -0.53
     einde
    -0.52
    $_['
    -0.52
    ávajú
    -0.51
     Edwards
    -0.50
    POSITIVE LOGITS
     noDo
    0.71
     חיצוניים
    0.69
     متعلقه
    0.65
     typelib
    0.65
     photolibrary
    0.64
    gdx
    0.64
    riwal
    0.64
    ztály
    0.63
     marinho
    0.63
    jemah
    0.61
    Act Density 0.255%

    No Known Activations