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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '../../../
    -0.07
    ии
    -0.07
     hinted
    -0.07
    secondary
    -0.07
    _DESTROY
    -0.07
    087
    -0.07
     imagePath
    -0.06
    WARN
    -0.06
     Runs
    -0.06
     použít
    -0.06
    POSITIVE LOGITS
    Tumblr
    0.06
     ｰ
    0.06
    mmo
    0.06
    Every
    0.06
    "Some
    0.06
     simulated
    0.06
    ”.
    0.06
     General
    0.05
     piyas
    0.05
    orna
    0.05
    Act Density 0.008%

    No Known Activations