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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一页
    -0.06
    She
    -0.06
     cumpl
    -0.06
    stal
    -0.06
    ocaust
    -0.06
    �
    -0.06
    pon
    -0.06
    Ro
    -0.06
    рія
    -0.06
     गई
    -0.06
    POSITIVE LOGITS
     enact
    0.07
    challenge
    0.06
     incentiv
    0.06
    人は
    0.06
    ользов
    0.06
    icional
    0.06
    	exports
    0.06
    (args
    0.06
    Create
    0.06
    _internal
    0.06
    Act Density 0.009%

    No Known Activations