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

    Neuronpedia

    INDEX
    Explanations

    pre-amplifier, lubrication, louver, profile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immersed
    0.78
    ]);
    0.77
    isierte
    0.75
    asambhavam
    0.73
    ۹
    0.73
     azules
    0.72
    utations
    0.72
    qualiter
    0.72
    faulse
    0.71
    ۱
    0.71
    POSITIVE LOGITS
    of
    0.94
    า
    0.81
     way
    0.79
     to
    0.76
    to
    0.73
    知道
    0.73
    اً
    0.72
    ง
    0.70
     financial
    0.68
    اج
    0.67
    Act Density 0.000%

    No Known Activations