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

    Neuronpedia

    INDEX
    Explanations

    code snippets and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    که
    0.82
     จำนวน
    0.68
     vigente
    0.67
    ش
    0.67
    یس
    0.64
     convivial
    0.64
    ам
    0.64
    тың
    0.64
    ला
    0.63
     elaboración
    0.63
    POSITIVE LOGITS
     on
    0.72
    G
    0.68
    D
    0.65
     in
    0.64
    6
    0.63
    F
    0.60
    s
    0.59
    4
    0.58
    દેશ
    0.55
    近
    0.54
    Act Density 0.005%

    No Known Activations