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

    Neuronpedia

    INDEX
    Explanations

    functionality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ohon
    -0.07
    essed
    -0.07
    issa
    -0.07
    ownload
    -0.07
    ồi
    -0.07
     province
    -0.07
    净
    -0.07
    oub
    -0.06
    贪
    -0.06
    	change
    -0.06
    POSITIVE LOGITS
     ию
    0.09
    международ
    0.08
    .").
    0.08
    🎼
    0.07
    並將
    0.07
    随手
    0.07
    ↵↵↵↵↵
    0.07
     bureaucratic
    0.07
     ואם
    0.07
    защит
    0.07
    Act Density 0.028%

    No Known Activations