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

    Neuronpedia

    INDEX
    Explanations

    Python package building/distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’urgence
    -0.08
    rok
    -0.08
    期限
    -0.08
    ネル
    -0.07
     revolutionary
    -0.07
    તિ
    -0.07
     จาก
    -0.07
     líderes
    -0.07
    (compare
    -0.07
     queim
    -0.07
    POSITIVE LOGITS
     seq
    0.09
     ידע
    0.08
     amateur
    0.08
    .types
    0.08
    ол
    0.08
    Installer
    0.07
    .Types
    0.07
     logiciel
    0.07
     compliant
    0.07
     amateurs
    0.07
    Act Density 0.001%

    No Known Activations