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

    Neuronpedia

    INDEX
    Explanations

    dot followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ેશન
    0.60
     세율
    0.59
     setContentView
    0.57
     voluntarios
    0.57
     fomentar
    0.56
    setopt
    0.55
     convection
    0.55
     piezo
    0.55
     dafür
    0.54
    مسه
    0.54
    POSITIVE LOGITS
    ToString
    0.88
    Get
    0.78
     valueForKey
    0.76
    get
    0.68
    toString
    0.67
    toLowerCase
    0.65
    getAttribute
    0.64
    to
    0.64
    hasOwnProperty
    0.63
    To
    0.58
    Act Density 0.086%

    No Known Activations