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

    Neuronpedia

    INDEX
    Explanations

    shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     книги
    -0.06
    реб
    -0.06
    writeln
    -0.06
    _phr
    -0.06
     Ambient
    -0.06
     MEDIATEK
    -0.06
     excuses
    -0.05
    第一次
    -0.05
    modify
    -0.05
    _ulong
    -0.05
    POSITIVE LOGITS
    lassian
    0.08
    ibilidad
    0.07
     Rocket
    0.07
    )}"↵
    0.07
    ">↵
    0.07
     \↵
    0.07
    ."
↵
    0.07
    pecially
    0.06
     EG
    0.06
    ious
    0.06
    Act Density 0.036%

    No Known Activations