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

    Neuronpedia

    INDEX
    Explanations

    роб

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thuis
    -0.06
    全天
    -0.06
    Mus
    -0.06
     llevar
    -0.06
    פוט
    -0.06
     coz
    -0.06
    دان
    -0.06
     Sword
    -0.06
    ']",
    -0.06
    增强
    -0.06
    POSITIVE LOGITS
     REPL
    0.08
    一句
    0.08
    不克不及
    0.07
    _ARB
    0.07
    (Dictionary
    0.07
     הד
    0.07
     Deprecated
    0.07
    GER
    0.07
     RELATED
    0.07
    /array
    0.07
    Act Density 0.019%

    No Known Activations