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

    Neuronpedia

    INDEX
    Explanations

    explanations of how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     liés
    0.75
     Loose
    0.72
    ský
    0.71
    Loose
    0.68
     relacionado
    0.67
    相关的
    0.66
    相关
    0.66
     hän
    0.66
     liitty
    0.65
    নেল
    0.65
    POSITIVE LOGITS
     how
    1.31
    ว่าจะ
    1.27
     determining
    1.25
     whether
    1.23
    ว่า
    1.16
     cuáles
    1.14
     cuál
    1.13
     deciding
    1.11
     determinar
    1.11
     combien
    1.10
    Act Density 0.335%

    No Known Activations