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

    Neuronpedia

    INDEX
    Explanations

    unsung hero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ز
    0.57
     trattamento
    0.54
    搔
    0.53
    드로
    0.52
     ساين
    0.50
     новые
    0.46
    دين
    0.46
     ядер
    0.46
    нити
    0.46
    드를
    0.45
    POSITIVE LOGITS
    y
    0.63
    brother
    0.59
    ab
    0.56
    6
    0.56
    ocracy
    0.54
    emic
    0.54
    5
    0.52
    ables
    0.52
    ometers
    0.52
     الماض
    0.51
    Act Density 0.000%

    No Known Activations