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

    Neuronpedia

    INDEX
    Explanations

    Instructions and learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ApplicationException
    -0.07
    _SERVICE
    -0.07
    extField
    -0.06
    播出
    -0.06
    ountains
    -0.06
    _xor
    -0.06
     unaware
    -0.06
    燈
    -0.06
    sut
    -0.06
    膻
    -0.06
    POSITIVE LOGITS
    获
    0.07
    一切
    0.07
     defaultstate
    0.07
    иков
    0.07
     allerdings
    0.07
     cru
    0.07
    inci
    0.07
     om
    0.07
    ными
    0.07
     dirección
    0.06
    Act Density 0.055%

    No Known Activations