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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    íme
    -0.07
     ší
    -0.07
    folder
    -0.06
    饭
    -0.06
    出口
    -0.06
    (out
    -0.06
    aha
    -0.06
     MonoBehaviour
    -0.06
     fon
    -0.06
     compiler
    -0.06
    POSITIVE LOGITS
     victories
    0.06
     Observable
    0.06
     Caval
    0.06
     برابر
    0.06
     detrimental
    0.06
     Therapy
    0.06
     threaded
    0.06
    表情
    0.06
     palms
    0.06
     ecological
    0.06
    Act Density 0.003%

    No Known Activations