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

    Neuronpedia

    INDEX
    Explanations

    top recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    property
    0.75
    alne
    0.73
     टाइप्स
    0.73
    Property
    0.72
     Property
    0.72
     property
    0.69
     Efficient
    0.69
    oq
    0.68
     Tag
    0.67
     QT
    0.67
    POSITIVE LOGITS
     dais
    0.73
    یث
    0.73
    killer
    0.70
     stake
    0.68
    ਿਲ
    0.68
    whelming
    0.65
     Esteban
    0.65
     redemption
    0.64
    ♂
    0.64
     prel
    0.64
    Act Density 0.024%

    No Known Activations