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

    Neuronpedia

    INDEX
    Explanations

    words or terms related to substance or chemical compounds

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

    Letters followed by numbers or special characters

    np_acts-logits-general · gemini-2.0-flash

    Oetiker Boehringer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fully
    -0.67
    y
    -0.66
    に
    -0.65
    c
    -0.64
    -------------</
    -0.62
    是
    -0.61
    v
    -0.61
    p
    -0.61
    Personendaten
    -0.60
    KommentareTeilen
    -0.59
    POSITIVE LOGITS
    poe
    0.57
    gee
    0.54
    GEO
    0.53
    elp
    0.52
     tides
    0.51
    gemä
    0.51
    transforms
    0.51
    nhi
    0.50
    Ảnh
    0.50
    zeka
    0.50
    Act Density 0.300%

    No Known Activations