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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вано
    -0.06
     Burlington
    -0.06
     Francesco
    -0.06
     ATI
    -0.06
     unethical
    -0.06
    θρω
    -0.06
     souls
    -0.06
    포
    -0.06
    しまう
    -0.06
     ترك
    -0.06
    POSITIVE LOGITS
     gratuito
    0.07
    ,q
    0.07
    .safe
    0.07
     Clin
    0.07
    _Box
    0.07
    ologic
    0.06
    prototype
    0.06
     slab
    0.06
     infinitely
    0.06
     bastard
    0.06
    Act Density 0.006%

    No Known Activations