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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions and considerations related to technology and its applications in various contexts.

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

    introducing structured breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consumes
    0.37
     acrobat
    0.37
     nourishing
    0.37
    .$(
    0.36
     gyr
    0.36
    ار
    0.36
     зро
    0.36
     convolutions
    0.36
     labyr
    0.35
    ارية
    0.35
    POSITIVE LOGITS
    ’
    0.64
    Let
    0.44
    o
    0.44
     is
    0.43
    Here
    0.43
    nc
    0.41
    si
    0.41
    ano
    0.40
    ce
    0.39
    cd
    0.39
    Act Density 0.243%

    No Known Activations