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

    Neuronpedia

    INDEX
    Explanations

    Bracketed numbers and non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ([{
    -0.09
     mudar
    -0.08
     ઓળ
    -0.08
    ixar
    -0.08
     foli
    -0.08
     iarraidh
    -0.08
    ัง
    -0.08
    iyana
    -0.08
     चाहे
    -0.08
     rechercher
    -0.08
    POSITIVE LOGITS
     substituted
    0.08
     substitution
    0.07
     assistant
    0.07
     Pure
    0.07
    담
    0.07
    super
    0.07
     Replace
    0.07
     override
    0.07
    pure
    0.07
     super
    0.07
    Act Density 0.003%

    No Known Activations