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

    Neuronpedia

    INDEX
    Explanations

    code vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .onNext
    -0.07
     Separ
    -0.06
     Бер
    -0.06
    “There
    -0.06
    "..
    -0.06
    _gap
    -0.06
    ====
    -0.06
    .IsEnabled
    -0.05
    .sendKeys
    -0.05
    —with
    -0.05
    POSITIVE LOGITS
    太郎
    0.08
     	↵
    0.07
    hattan
    0.07
    Existing
    0.07
    ruby
    0.07
    flags
    0.06
    سی
    0.06
    lit
    0.06
    default
    0.06
    */
↵
↵
    0.06
    Act Density 0.001%

    No Known Activations