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

    Neuronpedia

    INDEX
    Explanations

    function inputs and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াসেব
    0.37
    スナー
    0.37
     kı
    0.36
    जफ्
    0.36
    ബരി
    0.36
     कार्यकारिणी
    0.35
     cuarta
    0.35
    汼
    0.35
     조성
    0.34
     সমাবেশ
    0.34
    POSITIVE LOGITS
     inputs
    0.82
     accepts
    0.78
     Inputs
    0.76
     input
    0.72
    输入
    0.69
    input
    0.68
    inputs
    0.68
     принимает
    0.67
     输入
    0.67
     accepting
    0.66
    Act Density 0.007%

    No Known Activations