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

    Neuronpedia

    INDEX
    Explanations

    the word "almost" and its variations

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

    nearness or approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PDC
    -0.37
     ayrıca
    -0.36
     discipline
    -0.36
     PDC
    -0.35
     Vaters
    -0.34
    geber
    -0.33
     Schild
    -0.32
     cadre
    -0.32
     Dutton
    -0.32
     Discipline
    -0.32
    POSITIVE LOGITS
    Almost
    1.09
     nearly
    1.05
     almost
    1.05
    almost
    1.05
     Almost
    1.00
    nearly
    1.00
     Nearly
    1.00
    Nearly
    1.00
    Casi
    0.95
     presque
    0.90
    Act Density 0.015%

    No Known Activations