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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обл
    -0.07
    _rand
    -0.06
    494
    -0.06
    -A
    -0.06
     poem
    -0.06
     MARK
    -0.06
     OVER
    -0.06
    .build
    -0.06
    .Stream
    -0.06
    ورن
    -0.06
    POSITIVE LOGITS
     direccion
    0.07
     společnosti
    0.07
    cılık
    0.06
     MM
    0.06
     підтрим
    0.06
    Club
    0.06
     července
    0.06
     spoilers
    0.06
     dej
    0.06
    -awaited
    0.06
    Act Density 0.079%

    No Known Activations