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

    Neuronpedia

    INDEX
    Explanations

    broad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isser
    -0.27
    TERS
    -0.25
    åħ¨åľº
    -0.25
     original
    -0.24
    åİŁ
    -0.24
     fo
    -0.24
    空
    -0.24
     separated
    -0.23
    /rest
    -0.23
    Ã¶ÄŁ
    -0.23
    POSITIVE LOGITS
    caster
    0.31
    storm
    0.28
    Impact
    0.27
    ridge
    0.26
    gest
    0.26
     Sherman
    0.25
    board
    0.23
    é¦Ĵ
    0.23
    wire
    0.23
    mite
    0.23
    Act Density 0.014%

    No Known Activations