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

    Neuronpedia

    INDEX
    Explanations

    advertising

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ing
    -0.08
     Time
    -0.07
     :\
    -0.07
    /Dk
    -0.07
    irts
    -0.07
    瑖
    -0.06
    -move
    -0.06
    forcement
    -0.06
    .ejb
    -0.06
    _SHIFT
    -0.06
    POSITIVE LOGITS
    أزمة
    0.07
     evapor
    0.07
     jsonObject
    0.07
     separator
    0.07
    -cn
    0.07
    interface
    0.07
     cron
    0.07
    Mus
    0.06
    感受到
    0.06
     induced
    0.06
    Act Density 0.032%

    No Known Activations