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

    Neuronpedia

    INDEX
    Explanations

    Numbers close to zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reflections
    -0.08
     grooming
    -0.08
     روا
    -0.08
    多久
    -0.07
     jargon
    -0.07
    Cu
    -0.07
    (review
    -0.07
     Rä
    -0.07
     Denim
    -0.07
    小
    -0.07
    POSITIVE LOGITS
     obedient
    0.08
    essel
    0.08
     departing
    0.08
     ಇಲಾಖೆ
    0.08
     Unary
    0.08
     intersects
    0.08
     crédit
    0.08
     ಇಲಾಖ
    0.07
     unary
    0.07
     dishonest
    0.07
    Act Density 0.001%

    No Known Activations