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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to electron interactions and their effects in physics

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

    Follows prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    research contribution and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muß
    -0.94
     idéia
    -0.85
    faßt
    -0.83
     daß
    -0.83
     Einfluß
    -0.76
     biß
    -0.71
     läßt
    -0.71
     Moslem
    -0.65
     Schluß
    -0.63
     müßte
    -0.63
    POSITIVE LOGITS
     incentiv
    0.99
     leveraging
    0.95
     Notably
    0.95
     impactful
    0.88
     autorytatywna
    0.87
     nuanced
    0.84
     microbiome
    0.82
    NameInMap
    0.81
     '\\;'
    0.78
    nullptr
    0.78
    Act Density 3.703%

    No Known Activations