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

    Neuronpedia

    INDEX
    Explanations

    variable or function names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lead
    0.70
    Lead
    0.63
    鲢
    0.62
    colFirst
    0.59
     lead
    0.58
     endorsing
    0.58
    wch
    0.57
    opters
    0.56
     ballast
    0.56
    vm
    0.56
    POSITIVE LOGITS
    __(
    0.72
     কর্তৃপক্ষের
    0.59
    ហា
    0.58
    __.
    0.58
    __()
    0.58
    సై
    0.58
    ហ
    0.57
    <0xA2>
    0.56
     un
    0.56
     ανα
    0.56
    Act Density 0.228%

    No Known Activations