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

    Neuronpedia

    INDEX
    Explanations

    value and "valuable"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.71
    with
    0.66
    N
    0.66
    D
    0.65
    ng
    0.57
    V
    0.57
    C
    0.57
    T
    0.57
    الش
    0.55
    ässig
    0.55
    POSITIVE LOGITS
    ล
    0.84
     değeri
    0.78
     valuation
    0.75
     VALUE
    0.75
     value
    0.73
     valu
    0.73
    '
    0.68
     trove
    0.66
     Valuation
    0.65
    רג
    0.65
    Act Density 0.122%

    No Known Activations