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

    Neuronpedia

    INDEX
    Explanations

    configuration levels keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hamburgers
    0.46
     thanksgiving
    0.43
     rapping
    0.42
    '
    0.41
     myogenic
    0.41
    eleration
    0.41
     anything
    0.40
     eaten
    0.39
     internship
    0.38
     unbounded
    0.38
    POSITIVE LOGITS
     Mā
    0.50
     Kä
    0.49
    难
    0.47
     Ва
    0.46
     Fäh
    0.45
     Fehler
    0.45
     Kür
    0.45
     Ги
    0.44
     Фе
    0.44
     recuperação
    0.43
    Act Density 0.006%

    No Known Activations