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

    Neuronpedia

    INDEX
    Explanations

    foreign language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adjective
    -0.07
    ेह
    -0.07
     дней
    -0.07
    .isDebugEnabled
    -0.07
    outputs
    -0.07
    sy
    -0.06
    рахов
    -0.06
    ographer
    -0.06
     rugs
    -0.06
    ifer
    -0.06
    POSITIVE LOGITS
     unic
    0.08
    _DIFF
    0.07
     電
    0.07
     언
    0.06
    ."""
    0.06
    aucoup
    0.06
    _##
    0.06
     décou
    0.06
    ereco
    0.06
     کم
    0.06
    Act Density 0.018%

    No Known Activations