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

    Neuronpedia

    INDEX
    Explanations

    character names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generado
    0.41
     microbiological
    0.39
     macroeconomic
    0.38
     anek
    0.37
    힝
    0.37
     implementations
    0.36
     microorgan
    0.36
     SupCt
    0.36
     frontend
    0.35
    cparam
    0.35
    POSITIVE LOGITS
     Caspian
    0.46
     muttered
    0.46
    Ethan
    0.45
     Finn
    0.44
     Kai
    0.44
    Violet
    0.44
    Indigo
    0.44
    Liam
    0.44
     Luna
    0.44
     Skye
    0.43
    Act Density 0.045%

    No Known Activations