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

    Neuronpedia

    INDEX
    Explanations

    coding and lineage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tei
    0.75
    ceti
    0.75
    ICOS
    0.71
     Tại
    0.70
    टि
    0.70
    ே
    0.70
    ﻄ
    0.70
     Tetapi
    0.69
     Vestone
    0.69
     Bugün
    0.68
    POSITIVE LOGITS
     kickoff
    0.78
     uses
    0.76
     si
    0.74
     maintenance
    0.73
    徑
    0.73
     cashback
    0.71
     wskaz
    0.70
     shrub
    0.69
     considérons
    0.69
     ñ
    0.68
    Act Density 0.001%

    No Known Activations