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

    Neuronpedia

    INDEX
    Explanations

    There, could, only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    établir
    0.89
    ']])
    0.87
    ')){
    0.78
     schließen
    0.77
    olit
    0.77
     Cubic
    0.77
    <unused68>
    0.76
    <unused92>
    0.76
    derived
    0.75
    ँचा
    0.75
    POSITIVE LOGITS
     dances
    0.73
     conhece
    0.71
     sadece
    0.70
     understand
    0.70
     etapa
    0.70
     dies
    0.67
    CharSequence
    0.67
     apenas
    0.66
     muere
    0.62
    로
    0.62
    Act Density 0.000%

    No Known Activations