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

    Neuronpedia

    INDEX
    Explanations

    legal case descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     праздник
    -0.07
    く
    -0.07
     pessoa
    -0.07
     Callable
    -0.07
     Slovak
    -0.07
    ڪ
    -0.06
     catalogue
    -0.06
    eğ
    -0.06
    _sql
    -0.06
     日
    -0.06
    POSITIVE LOGITS
     pedals
    0.07
    武装
    0.07
    Remaining
    0.07
    riminal
    0.07
    干扰
    0.06
     disciplines
    0.06
     interrupts
    0.06
     ignition
    0.06
     Wireless
    0.06
    .Infrastructure
    0.06
    Act Density 0.019%

    No Known Activations