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

    Neuronpedia

    INDEX
    Explanations

    terms related to size classifications

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

    describing magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Referencie
    -0.52
     aguja
    -0.49
    <bos>
    -0.48
    >{@
    -0.48
    knex
    -0.47
     enggak
    -0.47
     hjär
    -0.46
     Arhi
    -0.45
    Gruß
    -0.45
     vecka
    -0.43
    POSITIVE LOGITS
    sized
    1.91
     sized
    1.80
    Sized
    1.58
    sizing
    1.01
     Sizing
    0.92
    Sizing
    0.85
    サイズの
    0.84
    sizes
    0.81
     sizing
    0.79
     oversized
    0.78
    Act Density 0.010%

    No Known Activations