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

    Neuronpedia

    INDEX
    Explanations

    Code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khắc
    -0.07
    ҝ
    -0.07
    ~-
    -0.07
    ퟬ
    -0.07
    كتروني
    -0.07
    ✓
    -0.07
     courtesy
    -0.07
    嵘
    -0.07
    關注
    -0.06
    +-
    -0.06
    POSITIVE LOGITS
    戒指
    0.08
    ANGE
    0.08
     XK
    0.07
    ativ
    0.07
    ITA
    0.07
     zap
    0.07
    oldem
    0.07
     להש
    0.07
     exposition
    0.07
    Rotation
    0.07
    Act Density 0.009%

    No Known Activations