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

    Neuronpedia

    INDEX
    Explanations

    numbers, siblings, or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    miller
    0.43
     Tripathi
    0.41
     வள்ளி
    0.40
    Absorption
    0.40
     Cria
    0.38
     UserController
    0.38
     deuxième
    0.38
     Absorption
    0.38
     forceps
    0.38
     troisième
    0.37
    POSITIVE LOGITS
     pictures
    0.41
     bur
    0.40
     অধীন
    0.39
     tangents
    0.38
     सतर्क
    0.38
    Pictures
    0.38
     длину
    0.38
    👖
    0.38
     aerospace
    0.37
    சன்
    0.36
    Act Density 0.000%

    No Known Activations