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

    Neuronpedia

    INDEX
    Explanations

    list items describing inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hilfre
    0.38
     ස
    0.37
     எச்ச
    0.37
     পিপ
    0.37
     actionBar
    0.36
    semble
    0.36
     أمر
    0.35
     hilfreich
    0.35
     sorprend
    0.35
     desempe
    0.35
    POSITIVE LOGITS
     input
    0.85
    输入
    0.83
    input
    0.82
     inputted
    0.80
    输入的
    0.76
     Input
    0.75
    Input
    0.73
     inputs
    0.73
     输入
    0.72
     incoming
    0.71
    Act Density 0.385%

    No Known Activations