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

    Neuronpedia

    INDEX
    Explanations

    verbs relating to intentions, capabilities, or characteristics in context

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

    purpose or composition phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juges
    -0.52
    ſelf
    -0.52
     ſtate
    -0.49
    StructEnd
    -0.48
     itſelf
    -0.47
     pleaſure
    -0.46
     Irán
    -0.46
     houſe
    -0.45
     enfans
    -0.44
     vectoriales
    -0.42
    POSITIVE LOGITS
    RegistryLite
    0.54
    NameValuePair
    0.51
     vorbei
    0.49
     consultato
    0.47
     Mid
    0.47
    phthal
    0.46
     '{@
    0.45
    ousands
    0.44
     незавершена
    0.44
    同じく
    0.44
    Act Density 0.291%

    No Known Activations