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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ל
    -0.07
    \'
    -0.07
    织
    -0.07
     tái
    -0.06
    底
    -0.06
    both
    -0.06
     حذف
    -0.06
    ková
    -0.06
    _COUNTER
    -0.06
     retrieving
    -0.06
    POSITIVE LOGITS
    --}}↵
    0.08
    _STACK
    0.07
    .Z
    0.06
    ==↵
    0.06
     furnace
    0.06
    .charCodeAt
    0.06
    ()};↵
    0.06
    .Dir
    0.06
    σε
    0.06
     bullshit
    0.06
    Act Density 0.020%

    No Known Activations