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

    Neuronpedia

    INDEX
    Explanations

    complex issues and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    warm
    0.52
    ב
    0.46
    ออกแบบ
    0.44
    ergy
    0.43
    baptism
    0.43
    म
    0.43
    metallic
    0.43
    ं
    0.43
    封
    0.42
    ゝ
    0.41
    POSITIVE LOGITS
     prüfe
    0.48
     Fehl
    0.45
     sentiment
    0.44
     Nirvana
    0.44
     chip
    0.44
     larger
    0.41
     provavelmente
    0.41
     vermutlich
    0.41
     wahrscheinlich
    0.41
     cez
    0.41
    Act Density 0.015%

    No Known Activations