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

    Neuronpedia

    INDEX
    Explanations

    SM, Sam, San, Sanit prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Método
    0.52
    endung
    0.43
    ünüz
    0.43
     TouchUtils
    0.43
     FabD
    0.42
    岕
    0.42
    ScienceStudent
    0.40
    ുകളിൽ
    0.39
    روش
    0.39
     Metode
    0.39
    POSITIVE LOGITS
     sm
    0.65
     Sm
    0.55
     SM
    0.53
    San
    0.53
    Sm
    0.51
     San
    0.50
    سم
    0.47
     SMB
    0.47
     sanctuaries
    0.47
    SM
    0.45
    Act Density 0.037%

    No Known Activations