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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cine
    -0.09
     Cine
    -0.08
    .nz
    -0.08
     Kalau
    -0.08
    ーズ
    -0.07
    Nz
    -0.07
     fiquei
    -0.07
     verdadeira
    -0.07
     иҷро
    -0.07
                           ↵
    -0.07
    POSITIVE LOGITS
    স্থান
    0.08
    车型
    0.07
     esteem
    0.07
    .binding
    0.07
    0.07
     divine
    0.07
    станов
    0.07
     съд
    0.07
     stereotypes
    0.07
     Steel
    0.07
    Act Density 0.003%
    No Known Activations