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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marketed
    -0.07
    أت
    -0.07
     method
    -0.06
    indexes
    -0.06
    жения
    -0.06
    est
    -0.06
     Cond
    -0.06
    -case
    -0.06
    范
    -0.06
    оступ
    -0.06
    POSITIVE LOGITS
     Crowley
    0.07
     ries
    0.06
     drib
    0.06
    =edge
    0.06
     Oliveira
    0.06
     �
    0.06
    xEA
    0.06
     کیل
    0.06
     Religious
    0.06
    opolitan
    0.06
    Act Density 0.021%

    No Known Activations