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

    Neuronpedia

    INDEX
    Explanations

    HOME to crisis text line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सिंपली
    0.89
    rieron
    0.82
     gelegen
    0.80
    KAM
    0.78
     descoper
    0.77
     AGR
    0.76
     gleichen
    0.75
    nehmens
    0.73
    itably
    0.73
    spielen
    0.73
    POSITIVE LOGITS
     épais
    0.86
    0.77
    ﷲ
    0.74
     sobreviv
    0.72
    Stability
    0.69
     suic
    0.69
    र्वाद
    0.69
    ૪
    0.68
    three
    0.68
    টাইমস
    0.68
    Act Density 0.003%

    No Known Activations