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

    Neuronpedia

    INDEX
    Explanations

    hypothesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mmc
    -0.08
    とっても
    -0.08
    江淮
    -0.08
    长三角
    -0.08
     Camb
    -0.07
    "${
    -0.07
    Tar
    -0.07
    BCM
    -0.07
    aky
    -0.07
    但也
    -0.07
    POSITIVE LOGITS
     açıs
    0.07
    [Boolean
    0.07
     hypotheses
    0.07
    _hub
    0.07
     özelli
    0.07
    说
    0.07
    ℎ
    0.07
     integerValue
    0.07
    _InternalArray
    0.07
    _hp
    0.07
    Act Density 0.008%

    No Known Activations