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

    Neuronpedia

    INDEX
    Explanations

    software extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.90
     trimmer
    0.77
     clipper
    0.76
    ي
    0.75
     Biblia
    0.74
     copier
    0.69
     lanza
    0.68
     limpieza
    0.68
     goomba
    0.67
    iť
    0.67
    POSITIVE LOGITS
    (
    0.77
    sc
    0.76
    t
    0.69
    ction
    0.69
    lerin
    0.68
    -
    0.68
    inking
    0.68
    2
    0.67
    দ
    0.66
    aws
    0.66
    Act Density 0.003%

    No Known Activations