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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal numbers and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $*$-
    0.64
    IsResolver
    0.61
     exigences
    0.60
    pleClass
    0.60
    \%).
    0.59
     `:`,
    0.59
    \%$
    0.59
     unremarkable
    0.58
    *****",
    0.57
     neuronal
    0.57
    POSITIVE LOGITS
     (
    0.99
     =
    0.82
    .
    0.82
    ,
    0.78
    (
    0.74
    i
    0.71
    p
    0.70
    u
    0.69
    9
    0.68
    （
    0.67
    Act Density 0.001%

    No Known Activations