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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Прав
    -0.07
     Works
    -0.06
    naires
    -0.06
    ีย
    -0.06
     stands
    -0.06
    Mail
    -0.06
    imate
    -0.06
     search
    -0.06
    _param
    -0.06
     المدينة
    -0.06
    POSITIVE LOGITS
    CLE
    0.07
    lesi
    0.07
    elson
    0.07
    llvm
    0.06
     ه
    0.06
    LOSE
    0.06
    เส
    0.06
    elapsed
    0.06
    .Dec
    0.06
     Hoe
    0.06
    Act Density 0.079%

    No Known Activations