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

    Neuronpedia

    INDEX
    Explanations

    Gemma team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.14
    प
    1.05
    forces
    1.03
     fikir
    0.88
    اه
    0.88
     Coelho
    0.88
    z
    0.88
    je
    0.86
    ה
    0.85
    된
    0.85
    POSITIVE LOGITS
    ри
    0.98
    hentication
    0.93
     boomers
    0.90
    neſs
    0.87
    ності
    0.87
    менение
    0.86
     রাণী
    0.86
     患者
    0.85
    HLIGHT
    0.85
     cGraph
    0.84
    Act Density 0.005%

    No Known Activations