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

    Neuronpedia

    INDEX
    Explanations

    elements related to determination and effort in achieving goals

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

    after negations or limiting words

    np_acts-logits-general · gemini-2.0-flash

    lots of, know why, after some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.75
    enoord
    -0.74
     oprot
    -0.73
    WireFormatLite
    -0.68
     étoient
    -0.67
     auroit
    -0.67
     pouvoit
    -0.66
    enterOuterAlt
    -0.64
     étoit
    -0.62
    Vidite
    -0.62
    POSITIVE LOGITS
     utafitiHapana
    0.63
    hdashline
    0.60
     even
    0.60
    .$,
    0.60
    NUMX
    0.57
     etc
    0.56
    そして
    0.56
     فريبيس
    0.56
    </thead>
    0.55
     Etc
    0.55
    Act Density 0.426%

    No Known Activations