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

    Neuronpedia

    INDEX
    Explanations

    patterns and sequences in datasets or numerical information

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

    code and numerical data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ostavi
    -0.52
     AssemblyCulture
    -0.52
    dafx
    -0.46
    ########.
    -0.46
    :✨
    -0.44
    lismo
    -0.39
    Попис
    -0.38
    rawDesc
    -0.35
     agrí
    -0.33
    =-=-
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.59
     विश्वसनीयता
    0.57
    Legături
    0.48
    httphttps
    0.47
    findpost
    0.47
    뀜
    0.46
     Bewußt
    0.46
     AssertionError
    0.46
    fjspx
    0.45
    uxxxx
    0.45
    Act Density 0.335%

    No Known Activations