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

    Neuronpedia

    INDEX
    Explanations

    specific multi-word phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MYSQL
    0.53
    煐
    0.52
    ्रेडिट
    0.50
    郆
    0.48
    䤃
    0.48
    荇
    0.48
    MYSQL
    0.47
    筤
    0.47
    捪
    0.47
     funktionieren
    0.46
    POSITIVE LOGITS
    ze
    0.52
    '
    0.48
    uki
    0.46
    iego
    0.45
    bars
    0.45
    ar
    0.44
    vil
    0.44
    ares
    0.44
    peror
    0.44
    udi
    0.44
    Act Density 0.000%

    No Known Activations