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

    Neuronpedia

    INDEX
    Explanations

    module

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uez
    -0.07
    actus
    -0.07
    hosts
    -0.07
     impres
    -0.07
    พระ
    -0.06
    ⻁
    -0.06
     Fiction
    -0.06
     idols
    -0.06
     länger
    -0.06
    的带领
    -0.06
    POSITIVE LOGITS
    _DISPLAY
    0.08
     Pew
    0.07
     Deborah
    0.07
    IQUE
    0.07
    "Yeah
    0.07
    bursement
    0.06
    民政局
    0.06
     Hi
    0.06
    BIN
    0.06
     OG
    0.06
    Act Density 0.001%

    No Known Activations