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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantities or definitions

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

    collecting mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invis
    -0.48
    uesia
    -0.48
    cèse
    -0.47
    Indented
    -0.44
    InjectAttribute
    -0.43
     Stopped
    -0.43
     Pulver
    -0.42
    losion
    -0.42
    liceerd
    -0.41
     vân
    -0.41
    POSITIVE LOGITS
     term
    1.76
     terms
    1.63
     Term
    1.48
    Term
    1.45
    Terms
    1.42
    terms
    1.41
    term
    1.40
     Terms
    1.40
     término
    1.30
     TERMS
    1.30
    Act Density 0.080%

    No Known Activations