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

    Neuronpedia

    INDEX
    Explanations

    competition, reliable, dealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     so
    0.30
    so
    0.30
     Så
    0.27
    bottom
    0.27
     Has
    0.27
     after
    0.26
    day
    0.26
    )。
    0.26
    will
    0.26
     id
    0.26
    POSITIVE LOGITS
    ونت
    0.26
     шкі
    0.26
    医学
    0.25
     inglés
    0.25
    цин
    0.25
    кси
    0.25
     openness
    0.25
     clínico
    0.24
     vadanti
    0.24
     estudia
    0.24
    Act Density 0.013%

    No Known Activations