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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ätze
    -0.07
     flam
    -0.07
    (Name
    -0.07
    omore
    -0.06
    'utilisateur
    -0.06
    یمی
    -0.06
    fgang
    -0.06
     insurer
    -0.06
     کوت
    -0.06
    charge
    -0.06
    POSITIVE LOGITS
    irl
    0.07
    rices
    0.06
    og
    0.06
    ी,
    0.06
     PROP
    0.06
     NSObject
    0.06
     opposed
    0.06
    тин
    0.06
    >>↵
    0.06
    _EL
    0.05
    Act Density 0.040%

    No Known Activations