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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing quantity or degree

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

    more than quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prochaines
    -0.47
    kjø
    -0.47
     nächste
    -0.47
    cetines
    -0.44
    enlace
    -0.44
     lâmpada
    -0.43
    Ethylbenzene
    -0.42
     Evaluación
    -0.42
     amanhã
    -0.42
     náv
    -0.42
    POSITIVE LOGITS
     than
    0.75
    enumi
    0.72
     nearly
    0.69
     Nearly
    0.67
     over
    0.64
    Nearly
    0.63
     ponad
    0.62
    nearly
    0.61
     THAN
    0.61
     Than
    0.60
    Act Density 0.015%

    No Known Activations