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

    Neuronpedia

    INDEX
    Explanations

    Permission to any person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ferien
    -0.78
    stderr
    -0.75
    邳
    -0.72
    anthrene
    -0.71
     Chartered
    -0.70
    ₂)
    -0.70
    lantern
    -0.69
    疱
    -0.69
    ऑ
    -0.67
    ços
    -0.66
    POSITIVE LOGITS
    ctivos
    0.76
     šir
    0.74
     verd
    0.73
    gars
    0.71
    Kop
    0.71
    бу
    0.69
    *@
    0.68
     Berg
    0.66
    ång
    0.65
     Traditions
    0.65
    Act Density 0.039%

    No Known Activations