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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     má
    -0.28
    -days
    -0.28
    mdi
    -0.28
    çŀĴ
    -0.26
     fishes
    -0.26
    -cat
    -0.25
     enumerable
    -0.24
    æĬµæĬĹ
    -0.24
    awk
    -0.24
    icated
    -0.24
    POSITIVE LOGITS
    ä¾
    0.28
    足
    0.26
    runner
    0.26
    ä¿ĥ
    0.25
    æĪ¿äº§
    0.25
    就好
    0.25
    elpers
    0.24
    è·Łè¿Ľ
    0.24
    _AB
    0.24
    SS
    0.24
    Act Density 0.002%

    No Known Activations