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

    Neuronpedia

    INDEX
    Explanations

    references to parameters, connections, or variables in a technical context

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

    prepositional phrases with articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     labor
    -0.40
     labour
    -0.37
     disc
    -0.36
     cash
    -0.35
     fri
    -0.32
     gum
    -0.30
     Cash
    -0.30
     tele
    -0.30
     mos
    -0.29
     civil
    -0.29
    POSITIVE LOGITS
     desmotivaciones
    0.75
     Chwiliwch
    0.64
     AssemblyCulture
    0.64
    AndEndTag
    0.63
     disambiguazione
    0.63
     Waſſer
    0.63
    ientras
    0.62
     صوتيه
    0.60
    ambién
    0.59
    rungsseite
    0.59
    Act Density 0.271%

    No Known Activations