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

    Neuronpedia

    INDEX
    Explanations

    locations and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avity
    -0.28
    è¯Ħ为
    -0.27
    shield
    -0.26
    çĹ´
    -0.25
    sci
    -0.25
    -project
    -0.25
    WORDS
    -0.24
    åįĴ
    -0.24
    _FIXED
    -0.23
     proj
    -0.23
    POSITIVE LOGITS
    IGO
    0.30
    edes
    0.28
    inde
    0.27
    ewan
    0.27
    anza
    0.27
    ards
    0.27
    说ä¸įåĩº
    0.26
    éo
    0.25
    *)&
    0.25
    交æµģ
    0.24
    Act Density 0.845%

    No Known Activations