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

    Neuronpedia

    INDEX
    Explanations

    sequences of zeros interspersed with other numerical values

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

    zeroes and nulls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſchen
    -0.75
    wiliwch
    -0.70
     CreateTagHelper
    -0.69
     esimer
    -0.69
     ſeine
    -0.67
    :✨
    -0.67
     Geſch
    -0.66
     puentes
    -0.66
    ✨:
    -0.65
     laſſen
    -0.65
    POSITIVE LOGITS
    0
    0.78
    xFFFF
    0.49
    xffff
    0.47
     zero
    0.44
     zeroes
    0.43
    FFFF
    0.41
     zeros
    0.40
     Millennium
    0.40
     FFFF
    0.39
    null
    0.38
    Act Density 0.046%

    No Known Activations