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

    Neuronpedia

    INDEX
    Explanations

    Sasha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بررسی
    -0.07
     Royal
    -0.07
     Alan
    -0.06
    алы
    -0.06
     offenses
    -0.06
    форм
    -0.06
    byterian
    -0.06
    ël
    -0.06
     Studi
    -0.06
     argued
    -0.06
    POSITIVE LOGITS
     MSD
    0.08
    asha
    0.07
    Snippet
    0.07
    CJK
    0.06
    [attr
    0.06
    CTSTR
    0.06
     adverts
    0.06
    apes
    0.06
    oshi
    0.06
    .Custom
    0.06
    Act Density 0.003%

    No Known Activations