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

    Neuronpedia

    INDEX
    Explanations

    questions and discussions related to methods, processes, and innovative techniques

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

    magic, illusions, and clever feats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ----</
    -0.57
    ArrowToggle
    -0.53
     recensione
    -0.50
    enterOuterAlt
    -0.49
    usercontent
    -0.48
     okuyayım
    -0.46
    Commission
    -0.46
    alyptus
    -0.45
     stimmt
    -0.44
    ChildScrollView
    -0.44
    POSITIVE LOGITS
     magic
    0.50
     disambiguazione
    0.47
     feats
    0.46
     technology
    0.45
     magical
    0.44
     marvel
    0.43
     magically
    0.41
     marvels
    0.40
     miracle
    0.40
     nakalista
    0.39
    Act Density 0.069%

    No Known Activations