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

    Neuronpedia

    INDEX
    Explanations

    words related to primary usage and major focus areas

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

    followed by prepositions specifying a cause or origin

    np_acts-logits-general · gemini-2.0-flash

    blame assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.77
    GraphicsUnit
    -0.68
    setof
    -0.61
    moveToFirst
    -0.60
     algum
    -0.58
     gesam
    -0.58
     nearest
    -0.58
     chiunque
    -0.57
     einz
    -0.57
     архивлан
    -0.57
    POSITIVE LOGITS
    +#+#
    0.67
     Blame
    0.64
    blame
    0.54
     λό
    0.54
     discours
    0.52
     blame
    0.51
    uttavia
    0.51
     rely
    0.51
    TAINMENT
    0.50
    prnewswire
    0.50
    Act Density 0.291%

    No Known Activations