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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation or admiration for qualities and characteristics

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

    how classichow realhow newhow powerhow psychological

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seat
    -0.33
    AppMethodBeat
    -0.33
    risch
    -0.32
    nsito
    -0.31
    exitRule
    -0.31
     tiket
    -0.30
    nsyn
    -0.30
    tibus
    -0.29
     tickets
    -0.29
    Giới
    -0.29
    POSITIVE LOGITS
     Normdatei
    0.69
     StatelessWidget
    0.68
    featureID
    0.62
    ftagPool
    0.56
    fortawesome
    0.53
     चीज़ों
    0.53
     nice
    0.52
    extAlignment
    0.52
    ValueStyle
    0.52
     onCancelled
    0.51
    Act Density 0.008%

    No Known Activations