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

    Neuronpedia

    INDEX
    Explanations

    novel and eclectic expressions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    articles and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üedad
    -0.39
     δύ
    -0.38
     either
    -0.36
    untung
    -0.35
     final
    -0.35
     eccell
    -0.35
     Small
    -0.34
     Either
    -0.33
     small
    -0.32
     hombro
    -0.32
    POSITIVE LOGITS
     kasarigan
    0.78
    ########.
    0.74
     chimpanze
    0.72
     dinosaur
    0.71
     underwater
    0.71
    なんと
    0.70
    underwater
    0.70
     bikini
    0.70
     penguins
    0.69
     bikinis
    0.69
    Act Density 0.215%

    No Known Activations