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

    Neuronpedia

    INDEX
    Explanations

    breaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ifad
    -0.07
    Num
    -0.07
    ackages
    -0.06
     naj
    -0.06
    _ends
    -0.06
    ião
    -0.06
    	pool
    -0.06
     absurd
    -0.06
    (Is
    -0.06
    demand
    -0.06
    POSITIVE LOGITS
     Smithsonian
    0.06
    ={}
    0.06
    blast
    0.06
    bol
    0.06
     baseline
    0.06
    新的
    0.06
    amation
    0.06
     hin
    0.06
    PLAIN
    0.06
    ricula
    0.06
    Act Density 0.003%

    No Known Activations