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

    Neuronpedia

    INDEX
    Explanations

    With

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Genesis
    -0.07
     yazar
    -0.07
    oute
    -0.07
     exact
    -0.07
     Huss
    -0.07
     genesis
    -0.07
     as
    -0.07
    ář
    -0.07
     Anonymous
    -0.06
     мам
    -0.06
    POSITIVE LOGITS
    With
    0.10
     With
    0.09
     символ
    0.07
    .Arg
    0.06
    Composite
    0.06
     ith
    0.06
     aktivit
    0.06
     with
    0.06
    Training
    0.06
     Điện
    0.06
    Act Density 0.029%

    No Known Activations