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

    Neuronpedia

    INDEX
    Explanations

    size and numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒆳
    0.42
    滏
    0.40
    诰
    0.39
     преимущества
    0.39
    WithFieldContext
    0.38
     Gesundheits
    0.38
    Très
    0.38
     حیر
    0.38
    婕
    0.38
     воспита
    0.38
    POSITIVE LOGITS
     digits
    0.55
     values
    0.54
     string
    0.52
     item
    0.52
     value
    0.51
     size
    0.51
     typed
    0.51
     was
    0.49
     wasn
    0.49
     be
    0.48
    Act Density 0.566%

    No Known Activations