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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    うち
    -0.07
     sortBy
    -0.06
     přiz
    -0.06
    .tp
    -0.06
     Pierce
    -0.06
    Ten
    -0.06
    .singletonList
    -0.06
     Ten
    -0.06
     Prevention
    -0.06
     BJP
    -0.06
    POSITIVE LOGITS
     fan
    0.06
    _DELTA
    0.06
    ennial
    0.06
    ocale
    0.06
    ragon
    0.06
    镜
    0.06
     Module
    0.06
     extrad
    0.06
    isLoading
    0.06
    eating
    0.06
    Act Density 0.005%

    No Known Activations