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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENA
    -0.07
    צהר
    -0.07
    Ẽ
    -0.07
    贼
    -0.07
     sắc
    -0.07
     evacuate
    -0.06
    prar
    -0.06
    ꦭ
    -0.06
     programas
    -0.06
     visita
    -0.06
    POSITIVE LOGITS
     grad
    0.07
     modest
    0.07
     Low
    0.07
    꼽
    0.07
    などが
    0.07
     kaz
    0.07
    Some
    0.07
    들을
    0.06
    !),
    0.06
     Люб
    0.06
    Act Density 0.001%

    No Known Activations