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

    Neuronpedia

    INDEX
    Explanations

    default values in programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JOR
    -0.08
     treb
    -0.08
     Ju
    -0.08
     juice
    -0.08
     Jade
    -0.08
     suspensión
    -0.08
     раст
    -0.08
    شهد
    -0.07
     куз
    -0.07
    قت
    -0.07
    POSITIVE LOGITS
     默认
    0.15
    (default
    0.15
    Defaults
    0.15
    "default
    0.15
    'default
    0.14
    默认
    0.14
    default
    0.14
     Defaults
    0.14
    /default
    0.14
     default
    0.14
    Act Density 0.013%

    No Known Activations