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

    Neuronpedia

    INDEX
    Explanations

    switch (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sa
    0.58
     ampere
    0.50
    ,\
    0.49
     Spokes
    0.47
    諾
    0.47
    nv
    0.46
    ce
    0.46
    ವರೆ
    0.45
     adenine
    0.45
    าย
    0.45
    POSITIVE LOGITS
    끔
    0.55
    ول
    0.54
     proposés
    0.52
    モード
    0.52
    $+
    0.50
    (
    0.50
    ၃
    0.50
    ᑲ
    0.49
     (
    0.49
    딸
    0.48
    Act Density 0.000%

    No Known Activations