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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    faq
    -0.07
     mills
    -0.06
    атку
    -0.06
     stab
    -0.06
    kap
    -0.06
     único
    -0.06
    енд
    -0.06
     конце
    -0.06
     moi
    -0.06
    Charset
    -0.06
    POSITIVE LOGITS
    .Event
    0.07
    един
    0.07
    .Ο
    0.06
    //{↵
    0.06
    _<
    0.06
    _SENSOR
    0.06
     Added
    0.06
    [right
    0.06
    location
    0.06
     انگ
    0.06
    Act Density 0.047%

    No Known Activations