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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lester
    -0.08
    这种事情
    -0.07
    力还是自
    -0.07
     notion
    -0.07
    Sean
    -0.07
    Dealer
    -0.07
    色情
    -0.07
    connecting
    -0.07
    +k
    -0.07
    双脚
    -0.07
    POSITIVE LOGITS
    1
    0.09
     Lomb
    0.09
    ́
    0.08
    _internal
    0.08
    流
    0.07
    i
    0.07
    �
    0.07
    �
    0.07
     Smithsonian
    0.07
     Dale
    0.07
    Act Density 0.258%

    No Known Activations