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

    Neuronpedia

    INDEX
    Explanations

    Reviews/Summaries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAYS
    -0.08
    ้ง
    -0.07
    に入る
    -0.07
    蛴
    -0.07
     '".
    -0.07
    ﱋ
    -0.07
    栊
    -0.07
    🌕
    -0.07
     millionaire
    -0.07
    فيديو
    -0.07
    POSITIVE LOGITS
     Slim
    0.07
    קי
    0.07
    Const
    0.07
    (const
    0.07
    _CERT
    0.07
    patial
    0.07
     asynchronously
    0.06
     Temp
    0.06
    Swipe
    0.06
    钳
    0.06
    Act Density 0.022%

    No Known Activations