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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通常
    -0.07
     Kentucky
    -0.07
     úda
    -0.06
    КА
    -0.06
     Nevada
    -0.06
    emain
    -0.06
    ン�
    -0.06
    pond
    -0.06
     Thánh
    -0.06
    кас
    -0.06
    POSITIVE LOGITS
     SINGLE
    0.07
     Drill
    0.06
    ENDED
    0.06
    )%
    0.06
    _sep
    0.06
    altimore
    0.06
    248
    0.06
    uality
    0.06
    urar
    0.06
    ’ll
    0.06
    Act Density 0.212%

    No Known Activations