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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َب
    -0.07
    hidden
    -0.07
     tolerate
    -0.06
     reput
    -0.06
     única
    -0.06
     devastated
    -0.06
     persuaded
    -0.06
    ствие
    -0.06
    acyj
    -0.06
     мас
    -0.06
    POSITIVE LOGITS
     swaps
    0.08
     enum
    0.08
     PAGE
    0.07
     yoksa
    0.07
    [edge
    0.07
    屋
    0.07
    ---------↵
    0.07
     oyn
    0.06
     basename
    0.06
     audition
    0.06
    Act Density 0.000%

    No Known Activations