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

    Neuronpedia

    INDEX
    Explanations

    tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heather
    -0.07
    /io
    -0.07
     саме
    -0.07
    LA
    -0.06
     deviations
    -0.06
     gad
    -0.06
    -la
    -0.06
     celkem
    -0.06
    yling
    -0.06
     bulls
    -0.06
    POSITIVE LOGITS
     Ś
    0.07
     kHz
    0.07
    เฮ
    0.07
    VERN
    0.06
    Κ
    0.06
    oine
    0.06
    efore
    0.06
     TFT
    0.06
    чив
    0.06
     дослідження
    0.06
    Act Density 0.000%

    No Known Activations