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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getLocation
    -0.08
     admirable
    -0.08
     drawable
    -0.07
     discretion
    -0.07
     tightened
    -0.07
     purposely
    -0.07
     над
    -0.07
    ngth
    -0.07
    Magnitude
    -0.07
    .Path
    -0.07
    POSITIVE LOGITS
    气候
    0.08
    🕸
    0.07
    星际
    0.07
     vill
    0.07
    蝼
    0.07
    (Seq
    0.07
    jąc
    0.07
    哮
    0.07
    ्र
    0.06
    F
    0.06
    Act Density 0.015%

    No Known Activations