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

    Neuronpedia

    INDEX
    Explanations

    or before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˛
    0.77
     TextAlign
    0.76
     happening
    0.75
     Hare
    0.74
     Kale
    0.73
    ﻅ
    0.72
    鉉
    0.72
     Lakes
    0.72
     פור
    0.71
     남
    0.71
    POSITIVE LOGITS
    是一
    0.64
     capacidad
    0.64
     partes
    0.63
    רה
    0.61
     capacidades
    0.61
    Gb
    0.59
     உள்ளிட்ட
    0.58
     समस्त
    0.58
     parts
    0.57
     niveaux
    0.56
    Act Density 0.026%

    No Known Activations