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

    Neuronpedia

    INDEX
    Explanations

    citrus fruits and aloe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ો
    1.94
    ן
    1.80
    ના
    1.79
    ated
    1.77
     corticosteroids
    1.75
    のである
    1.70
     visant
    1.61
    ভাবেই
    1.59
     paralelas
    1.59
     peripherals
    1.56
    POSITIVE LOGITS
    r
    2.05
    grimas
    1.87
     следует
    1.81
    其他
    1.79
    lı
    1.72
    лна
    1.68
     І
    1.67
    𝘈
    1.66
    те
    1.63
    los
    1.63
    Act Density 0.005%

    No Known Activations