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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Madd
    -0.08
    Lambda
    -0.07
    ⇩
    -0.07
    Dist
    -0.06
     craz
    -0.06
     Lanc
    -0.06
    IALIZ
    -0.06
    铼
    -0.06
    URIComponent
    -0.06
     commodo
    -0.06
    POSITIVE LOGITS
    購
    0.07
    loy
    0.07
     Infinite
    0.07
    说出
    0.07
     fork
    0.07
     generalize
    0.07
    (row
    0.07
     дост
    0.07
    ()+
    0.07
     crane
    0.06
    Act Density 0.013%

    No Known Activations