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

    Neuronpedia

    INDEX
    Explanations

    latex math or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.66
    .</
    0.63
    sin
    0.60
    ldots
    0.59
    psi
    0.57
    ().
    0.55
    して
    0.55
    sum
    0.54
    pi
    0.53
    λάβ
    0.53
    POSITIVE LOGITS
     ${\
    0.84
    mathsf
    0.80
     Cooley
    0.77
     Sankt
    0.77
    -{\
    0.76
     typeface
    0.75
     Oprah
    0.73
    کل
    0.73
     Familien
    0.72
    драт
    0.72
    Act Density 0.000%

    No Known Activations