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

    Neuronpedia

    INDEX
    Explanations

    central dogma of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KS
    0.45
    SPRAY
    0.45
    পান
    0.45
    ADER
    0.44
    輥
    0.44
     ,
    0.44
    LLS
    0.44
    hib
    0.43
    Help
    0.43
     дії
    0.43
    POSITIVE LOGITS
     sagitt
    0.50
     declinations
    0.50
     invariable
    0.49
     tuple
    0.48
    初心
    0.46
     cautionary
    0.45
     Royaume
    0.45
     simplic
    0.44
    ربی
    0.43
     категори
    0.43
    Act Density 0.001%

    No Known Activations