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

    Neuronpedia

    INDEX
    Explanations

    Sep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERRY
    -0.09
    court
    -0.08
    creating
    -0.07
    these
    -0.07
     všech
    -0.07
    ODY
    -0.07
    KEY
    -0.07
    roker
    -0.07
    itty
    -0.07
    事情
    -0.07
    POSITIVE LOGITS
     Feb
    0.12
     Jan
    0.12
     Sep
    0.12
     Oct
    0.12
     Apr
    0.12
     Nov
    0.11
     Aug
    0.11
    Apr
    0.10
     Dec
    0.10
    Feb
    0.10
    Act Density 0.032%

    No Known Activations