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

    Neuronpedia

    INDEX
    Explanations

    adelante, adicionales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bullet
    0.39
     envy
    0.39
     sync
    0.38
    Bullet
    0.38
     possibilities
    0.38
     мүм
    0.38
    isce
    0.37
     Bullet
    0.36
     exposure
    0.36
     sorted
    0.36
    POSITIVE LOGITS
    eud
    0.46
    ietro
    0.44
    iant
    0.43
    ivin
    0.43
    erez
    0.41
    emas
    0.41
    pción
    0.41
     ܗ
    0.41
    quire
    0.41
     Сури
    0.40
    Act Density 0.002%

    No Known Activations