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

    Neuronpedia

    INDEX
    Explanations

    ase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    4
    -0.09
    3
    -0.08
     ради
    -0.08
    2
    -0.08
    12
    -0.07
    132
    -0.07
     four
    -0.07
    REET
    -0.07
    24
    -0.07
     abnormal
    -0.07
    POSITIVE LOGITS
    st
    0.12
    ST
    0.11
    ast
    0.11
    se
    0.11
    ost
    0.11
    SE
    0.11
    ist
    0.11
    ust
    0.10
    sh
    0.10
    ison
    0.10
    Act Density 0.640%

    No Known Activations