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

    Neuronpedia

    INDEX
    Explanations

    asking for classification codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ාවිත
    0.50
     lembut
    0.49
    aciji
    0.47
    ikaze
    0.46
     demokrat
    0.46
    ്യം
    0.45
    ել
    0.44
     دھو
    0.44
    awesi
    0.43
    gmzy
    0.43
    POSITIVE LOGITS
     Codes
    0.44
    =(
    0.43
     seção
    0.42
     below
    0.42
     three
    0.41
    Codes
    0.41
    aterial
    0.40
     অথবা
    0.40
     numbered
    0.40
     codes
    0.40
    Act Density 0.002%

    No Known Activations