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

    Neuronpedia

    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fibonacci
    -0.09
    ustain
    -0.07
     vững
    -0.07
    ellschaft
    -0.07
    鄀
    -0.07
     tussen
    -0.07
    箬
    -0.07
     aerobic
    -0.07
     государственн
    -0.07
    -unstyled
    -0.07
    POSITIVE LOGITS
    ﺟ
    0.07
    不想
    0.07
     Fig
    0.07
     ct
    0.07
    넬
    0.07
     Claim
    0.07
    Data
    0.07
     Law
    0.06
    Fig
    0.06
    PUT
    0.06
    Act Density 0.016%

    No Known Activations