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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "distinct."

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

    Follows specific punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    big deal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']==
    -0.59
    </i>
    -0.49
    cep
    -0.49
    лян
    -0.48
    rice
    -0.47
    υτό
    -0.46
     never
    -0.45
    '>";
    -0.45
     NEVER
    -0.45
    ']):
    -0.45
    POSITIVE LOGITS
     anymore
    0.90
    AnimationsModule
    0.83
    TagMode
    0.80
    eabouts
    0.78
    ResumeLayout
    0.78
     continúas
    0.77
     lắm
    0.72
    empio
    0.71
    enumi
    0.69
     nemmeno
    0.67
    Act Density 0.163%

    No Known Activations