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

    Neuronpedia

    INDEX
    Explanations

    organizational objectives and nonfiction contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |.|.|
    0.42
    ierzchn
    0.39
    illery
    0.39
     крова
    0.38
    placeholder
    0.38
    agliari
    0.37
     платье
    0.36
    acios
    0.36
    ujjati
    0.36
     возь
    0.36
    POSITIVE LOGITS
     configs
    0.41
     Einführung
    0.41
     Present
    0.39
     config
    0.39
     nonzero
    0.38
     TestCase
    0.38
     Exercises
    0.38
     Szen
    0.38
     Encounter
    0.38
     Enter
    0.38
    Act Density 0.001%

    No Known Activations