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

    Neuronpedia

    INDEX
    Explanations

    ruining someone's life or career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    히
    1.54
    ход
    1.50
     puluh
    1.48
    wow
    1.46
    DUCTION
    1.41
    conj
    1.40
    ‘
    1.34
    lash
    1.31
    $[
    1.30
     replaceable
    1.30
    POSITIVE LOGITS
     havoc
    1.93
    ೆಂದು
    1.67
     composure
    1.60
     doom
    1.56
    ˏ
    1.55
     intentions
    1.54
    assara
    1.54
     headache
    1.52
    된
    1.51
     Samaritan
    1.51
    Act Density 0.053%

    No Known Activations