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

    Neuronpedia

    INDEX
    Explanations

    emergence and manifestation of phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.49
    -
    0.46
    \
    0.41
    נים
    0.36
    ו
    0.36
    ové
    0.34
    /
    0.33
    ד
    0.33
     Jenis
    0.33
     Precio
    0.33
    POSITIVE LOGITS
     ina
    0.36
     in
    0.35
     così
    0.35
    なか
    0.35
    IT
    0.34
     undeniably
    0.34
     compre
    0.33
     майже
    0.33
     calamity
    0.33
     awfully
    0.33
    Act Density 0.087%

    No Known Activations