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

    Neuronpedia

    INDEX
    Explanations

    Lee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保
    -0.08
     Bo
    -0.07
    ख
    -0.07
    .Bean
    -0.07
     Gardner
    -0.07
    proc
    -0.07
    新征程
    -0.07
    щ
    -0.07
    STA
    -0.07
    _session
    -0.07
    POSITIVE LOGITS
    就是因为
    0.09
     withdrawal
    0.08
     intertwined
    0.08
     rehabilit
    0.08
    必須
    0.07
     deton
    0.07
    تركيب
    0.07
     Verfügung
    0.07
     لذلك
    0.07
    سياسات
    0.07
    Act Density 0.006%

    No Known Activations