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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to understanding, explaining, and developing processes or methods

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

    getting and giving details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webtoken
    -0.51
     kaarangay
    -0.46
    chemise
    -0.46
    uxxxx
    -0.45
    хьтан
    -0.43
    Evening
    -0.43
     foams
    -0.42
     Dispens
    -0.42
    ھیے
    -0.42
    istible
    -0.41
    POSITIVE LOGITS
     detailed
    0.67
     various
    0.65
     details
    0.64
     detail
    0.58
     about
    0.55
    detailed
    0.54
     detailing
    0.54
     knowledge
    0.53
     things
    0.52
     detaylı
    0.50
    Act Density 0.020%

    No Known Activations