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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to "terms" and "definitions."

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

    term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Invis
    -0.62
    akis
    -0.60
     Goodrich
    -0.59
     Pio
    -0.58
     Bleeding
    -0.57
     Gug
    -0.57
    disse
    -0.57
    ilosop
    -0.56
     Gud
    -0.56
     Propagation
    -0.56
    POSITIVE LOGITS
     Term
    0.84
    Term
    0.84
     term
    0.82
    term
    0.80
     TERM
    0.80
    TERM
    0.79
     terms
    0.75
    terms
    0.65
     Terms
    0.62
    Terms
    0.60
    Act Density 0.045%

    No Known Activations