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

    Neuronpedia

    INDEX
    Explanations

    bool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    layın
    -0.07
     출시
    -0.07
     Conversion
    -0.07
     Disc
    -0.06
    OUTH
    -0.06
    trash
    -0.06
    oven
    -0.06
     generations
    -0.06
     ragazzi
    -0.06
    pras
    -0.06
    POSITIVE LOGITS
     entren
    0.06
    尖
    0.06
     ヾ
    0.06
    /lang
    0.06
    (atom
    0.05
    .createNew
    0.05
    kemiz
    0.05
     erfolgreich
    0.05
     aload
    0.05
    SSERT
    0.05
    Act Density 0.005%

    No Known Activations