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

    Neuronpedia

    INDEX
    Explanations

    questions that seek guidance or advice

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

    interrogative phrases related to seeking advice or recommendations

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

    what do/does/would questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.76
    writeFieldEnd
    -0.72
     somethin
    -0.70
    Something
    -0.69
    EndInit
    -0.67
    anything
    -0.67
     Axiom
    -0.66
     myſelf
    -0.65
    Anything
    -0.65
     StatefulWidget
    -0.65
    POSITIVE LOGITS
     happen
    0.77
     you
    0.70
     happened
    0.68
     else
    0.66
     we
    0.63
     happens
    0.62
     I
    0.57
     отлича
    0.53
    forRoot
    0.52
    lasyon
    0.52
    Act Density 0.018%

    No Known Activations