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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peny
    -0.09
     станов
    -0.08
     남
    -0.07
    cision
    -0.07
    を探
    -0.07
     mend
    -0.07
    <IActionResult
    -0.07
    장님
    -0.07
    rom
    -0.07
    アイテ
    -0.07
    POSITIVE LOGITS
     de
    0.08
    我可以
    0.08
    aec
    0.08
    -power
    0.07
     ordering
    0.07
     nilai
    0.07
    .cli
    0.07
    _flux
    0.07
    /~
    0.07
    .generated
    0.07
    Act Density 0.188%

    No Known Activations