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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    na
    -0.07
    oriented
    -0.07
     Frid
    -0.07
    Path
    -0.07
    .memo
    -0.06
    광
    -0.06
     جم
    -0.06
     투
    -0.06
    �
    -0.06
    伙
    -0.06
    POSITIVE LOGITS
     виконання
    0.07
     gradually
    0.07
    Color
    0.06
     стари
    0.06
    "log
    0.06
    newsletter
    0.06
     Selling
    0.06
     legend
    0.06
     Style
    0.06
     Erotische
    0.06
    Act Density 0.000%

    No Known Activations