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

    Neuronpedia

    INDEX
    Explanations

    Quantum physics/computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayload
    -0.28
    .$.
    -0.28
    å®ĮæĪIJ
    -0.28
    åĽ½æ°ijç»ıæµİ
    -0.26
    楫
    -0.26
     Complete
    -0.26
    complete
    -0.26
    plet
    -0.25
     complet
    -0.25
    æĴ°åĨĻ
    -0.25
    POSITIVE LOGITS
     Girlfriend
    0.27
    -rec
    0.27
    haven
    0.26
    ImageContext
    0.25
    usercontent
    0.25
    AFP
    0.25
    ä¼´
    0.24
    ä¸įæŃ»
    0.24
     Reco
    0.24
     sacked
    0.24
    Act Density 0.006%

    No Known Activations