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

    Neuronpedia

    INDEX
    Explanations

    phrasses with the word "terms of"

    oai_token-act-pair · gemini-2.0-flash

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.69
     pleaſure
    -0.67
    <bos>
    -0.67
     purpoſe
    -0.65
     ſever
    -0.63
     bogotá
    -0.61
     ſche
    -0.60
     themſelves
    -0.60
     greateſt
    -0.59
     occaf
    -0.58
    POSITIVE LOGITS
    Including
    0.55
     Including
    0.54
    enumi
    0.53
     BoxDecoration
    0.49
    包括
    0.48
     including
    0.47
    antaranya
    0.46
    toarele
    0.46
     INCLUDING
    0.46
    og
    0.45
    Act Density 2.262%

    No Known Activations