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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endsWith
    -0.07
     unleash
    -0.07
    ToShow
    -0.07
     Mongolia
    -0.07
     önc
    -0.07
     грун
    -0.06
     sudoku
    -0.06
    :href
    -0.06
     Jong
    -0.06
     тобі
    -0.06
    POSITIVE LOGITS
     hedef
    0.07
    .Id
    0.07
    NJ
    0.06
    WR
    0.06
    <i
    0.06
    quat
    0.06
    =\'
    0.06
    0.06
    ;}
    0.06
     PERF
    0.06
    Act Density 0.005%

    No Known Activations