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

    Neuronpedia

    INDEX
    Explanations

    AGI, D&D, roleplaying, SGD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쾺
    0.45
    雓
    0.41
    陝
    0.39
    呠
    0.38
    跹
    0.37
    InsertInt
    0.37
     சிவன்
    0.37
    JScripts
    0.37
    occan
    0.36
    朿
    0.36
    POSITIVE LOGITS
     SG
    2.88
     VG
    2.83
     FG
    2.77
     HG
    2.77
     PG
    2.72
     TG
    2.70
     DG
    2.69
     CG
    2.67
    SG
    2.66
     WG
    2.66
    Act Density 0.155%

    No Known Activations