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

    Neuronpedia

    INDEX
    Explanations

    key terms and references that indicate significant relationships or thresholds in data analysis

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

    above or below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.48
    twimg
    -0.45
     pungkas
    -0.41
    ритори
    -0.40
    layoutControl
    -0.40
     Verſ
    -0.40
     ſever
    -0.40
     Monfieur
    -0.39
     rodríguez
    -0.39
     odw
    -0.39
    POSITIVE LOGITS
    Above
    0.82
     Above
    0.82
    above
    0.78
     above
    0.76
     below
    0.68
    below
    0.67
    Tikang
    0.66
    Below
    0.65
     Below
    0.63
     ABOVE
    0.61
    Act Density 0.036%

    No Known Activations