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

    Neuronpedia

    INDEX
    Explanations

    articles such as "the" and "a"

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

    into the [noun/concept]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ähteet
    -0.76
     zijne
    -0.74
     enfans
    -0.73
     ſta
    -0.72
     avoient
    -0.72
     dezelve
    -0.69
     keber
    -0.69
     zoude
    -0.68
     calcetines
    -0.68
     ſal
    -0.66
    POSITIVE LOGITS
     into
    1.13
     INTO
    1.00
     Into
    0.97
    into
    0.91
    Into
    0.90
    INTO
    0.74
     in
    0.56
     onto
    0.56
    isIn
    0.55
     inta
    0.54
    Act Density 0.031%

    No Known Activations