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

    Neuronpedia

    INDEX
    Explanations

    README

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ขอบ
    -0.07
    titulo
    -0.07
    Imagen
    -0.07
    ቴ
    -0.07
     geleceği
    -0.07
     Państwo
    -0.07
    有自己的
    -0.07
    ��
    -0.07
    崾
    -0.07
     Matt
    -0.06
    POSITIVE LOGITS
     installations
    0.08
    _sphere
    0.08
     wohl
    0.07
     Dabei
    0.07
    水稻
    0.07
     firearms
    0.07
    &&
    0.07
    雇主
    0.07
     doctrines
    0.07
     risking
    0.07
    Act Density 0.001%

    No Known Activations