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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plugins
    -0.08
     adjustments
    -0.07
    .vs
    -0.06
    .file
    -0.06
     qualifications
    -0.06
    _latest
    -0.06
     dünyada
    -0.06
    γον
    -0.06
    alien
    -0.06
     licenses
    -0.06
    POSITIVE LOGITS
     �
    0.07
    OUTPUT
    0.07
     cogn
    0.07
     abduction
    0.07
     bracelets
    0.06
     кноп
    0.06
     香
    0.06
     Occ
    0.06
     synonymous
    0.06
    衆
    0.06
    Act Density 0.008%

    No Known Activations