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

    Neuronpedia

    INDEX
    Explanations

    asp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    4
    -0.08
    2
    -0.07
     --------
    -0.07
    REET
    -0.07
     ради
    -0.07
     aluminum
    -0.06
    132
    -0.06
     �
    -0.06
    3
    -0.06
     square
    -0.06
    POSITIVE LOGITS
    st
    0.13
    ST
    0.13
    SE
    0.12
    se
    0.12
    ast
    0.12
    son
    0.11
    ost
    0.11
    ст
    0.11
    so
    0.11
    sk
    0.11
    Act Density 0.587%

    No Known Activations