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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or values

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

    words from different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.57
    сылкі
    -0.53
     '\\;'
    -0.52
     Chwiliwch
    -0.52
     thiệu
    -0.51
    忑
    -0.51
    timedia
    -0.51
    vinfos
    -0.50
    PCell
    -0.49
    Gambas
    -0.48
    POSITIVE LOGITS
    antaranya
    0.41
     Kerja
    0.39
     conmigo
    0.38
    ValueStyle
    0.38
     levanta
    0.38
    了嗎
    0.37
     alimentaria
    0.36
     desnuda
    0.35
     alimentaire
    0.35
     amanhã
    0.35
    Act Density 0.012%

    No Known Activations