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

    Neuronpedia

    INDEX
    Explanations

    concepts and themes related to complexity and structure

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

    Follows certain verbs like "addressing" and "covers"

    np_acts-logits-general · gemini-2.0-flash

    encompassing various topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    -0.56
     másik
    -0.54
    ‘
    -0.48
    setUse
    -0.47
     /
    -0.47
     '
    -0.46
     jugo
    -0.46
     çık
    -0.46
     kötü
    -0.45
     /^
    -0.45
    POSITIVE LOGITS
     everything
    1.11
    owohl
    1.09
     zarówno
    1.02
     både
    1.02
    everything
    0.99
     sowohl
    0.98
     both
    0.96
    esterday
    0.94
    +#+
    0.94
     zowel
    0.94
    Act Density 0.441%

    No Known Activations