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

    Neuronpedia

    INDEX
    Explanations

    expressions of customer engagement and satisfaction

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

    invitations and offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <thead>
    -0.38
    奇
    -0.37
     kap
    -0.35
    SourceChecksum
    -0.35
     VP
    -0.35
    南
    -0.34
    肉
    -0.34
     pup
    -0.34
    科
    -0.33
    yp
    -0.33
    POSITIVE LOGITS
     MainAxisSize
    0.65
    ſelves
    0.63
    AnchorTagHelper
    0.60
    ſelf
    0.58
    EDEFAULT
    0.57
     Majefty
    0.54
     الحره
    0.53
    wiſe
    0.53
     ब्रेकडाउन
    0.53
     utafitiHapana
    0.53
    Act Density 0.009%

    No Known Activations