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

    Neuronpedia

    INDEX
    Explanations

    fixtures and hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secuencia
    0.58
     dispositivos
    0.52
     техника
    0.52
     tuve
    0.51
     פי
    0.51
     odre
    0.51
     بابەت
    0.50
     comprensión
    0.50
     pesawat
    0.50
     każde
    0.49
    POSITIVE LOGITS
    enzie
    0.53
    FontSize
    0.53
    ERA
    0.52
    Centers
    0.51
    RA
    0.50
     recru
    0.50
    zend
    0.50
    ere
    0.49
     mobility
    0.49
     denominations
    0.48
    Act Density 0.004%

    No Known Activations