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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erectile
    -0.07
    BackingField
    -0.07
    Cross
    -0.07
     Thương
    -0.06
    kých
    -0.06
     Clear
    -0.06
    ereotype
    -0.06
    クリ
    -0.06
     Genome
    -0.06
     relocated
    -0.06
    POSITIVE LOGITS
     valid
    0.14
     validity
    0.08
    Validity
    0.08
     Valid
    0.08
    vac
    0.07
     writeln
    0.07
     valide
    0.07
     bogus
    0.07
    240
    0.06
    .AD
    0.06
    Act Density 0.007%

    No Known Activations