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

    Neuronpedia

    INDEX
    Explanations

    cultural

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isure
    -0.08
    iệm
    -0.07
    sse
    -0.07
    ships
    -0.06
     td
    -0.06
     revisions
    -0.06
    -0.06
    variant
    -0.06
    -sector
    -0.06
    Impl
    -0.06
    POSITIVE LOGITS
    벨
    0.07
    ASP
    0.06
    AGON
    0.06
    agon
    0.06
     DEV
    0.06
     TRAIN
    0.06
    associated
    0.06
    бе
    0.06
     Casual
    0.06
     sympathy
    0.06
    Act Density 0.010%

    No Known Activations