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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “And
    -0.07
     urlencode
    -0.07
    ensive
    -0.07
    眠
    -0.06
    edb
    -0.06
    translation
    -0.06
    “They
    -0.06
    ,but
    -0.06
    それに
    -0.06
    ctic
    -0.06
    POSITIVE LOGITS
    🙉
    0.08
    -ap
    0.07
    PEG
    0.07
    .StartPosition
    0.07
     projectile
    0.07
    ᆼ
    0.07
     defaultProps
    0.07
     decre
    0.07
     RATE
    0.07
    -existing
    0.07
    Act Density 0.001%

    No Known Activations