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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یل
    -0.08
     �
    -0.06
    帕
    -0.06
     чем
    -0.06
    EVENT
    -0.06
     vzdělávání
    -0.06
     vrouwen
    -0.06
     이름
    -0.06
    zelf
    -0.06
    CallCheck
    -0.06
    POSITIVE LOGITS
     verify
    0.07
     "[%
    0.06
    acy
    0.06
     inferred
    0.06
    mention
    0.06
    [B
    0.06
         ↵↵
    0.06
     Require
    0.06
    {-
    0.06
     fores
    0.05
    Act Density 0.006%

    No Known Activations