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

    Neuronpedia

    INDEX
    Explanations

    chess notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ociety
    -0.07
    rather
    -0.07
    orado
    -0.07
    _IS
    -0.07
    aji
    -0.06
    ら
    -0.06
     бенз
    -0.06
    ategies
    -0.06
     Banco
    -0.06
    trees
    -0.06
    POSITIVE LOGITS
     ис
    0.07
     žal
    0.07
     bên
    0.06
     عمل
    0.06
    (od
    0.06
    .updated
    0.06
     Cloud
    0.06
     gateway
    0.06
    Den
    0.06
    ги
    0.06
    Act Density 0.001%

    No Known Activations