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

    Neuronpedia

    INDEX
    Explanations

    ending or reduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getLocal
    -0.07
    _install
    -0.07
    .INVISIBLE
    -0.07
    ataloader
    -0.07
    $h
    -0.06
     gmail
    -0.06
    uppies
    -0.06
     universal
    -0.06
    見える
    -0.06
    ",$
    -0.06
    POSITIVE LOGITS
    _ITEMS
    0.07
    衬衫
    0.07
     Jamaica
    0.07
    医学
    0.06
    paren
    0.06
    ícul
    0.06
    艰
    0.06
    lemetry
    0.06
    窃
    0.06
    dictions
    0.06
    Act Density 0.120%

    No Known Activations