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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jak
    -0.06
     عز
    -0.06
     проти
    -0.06
    ++;↵
    -0.06
    Cash
    -0.06
    ント
    -0.06
    AC
    -0.06
     Novel
    -0.06
    �
    -0.06
     highways
    -0.06
    POSITIVE LOGITS
    _typ
    0.08
     brav
    0.06
     "".
    0.06
    観
    0.06
    _PC
    0.06
    _↵
    0.06
    .Syntax
    0.06
     humiliating
    0.06
     vielleicht
    0.06
    reshape
    0.06
    Act Density 0.000%

    No Known Activations