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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific formatting symbols in text

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

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.54
     виправивши
    -0.54
    fromnode
    -0.52
    ReusableCell
    -0.50
    interopRequire
    -0.48
     betweenstory
    -0.48
     littéraire
    -0.48
     literario
    -0.47
     gabbana
    -0.47
     Infór
    -0.47
    POSITIVE LOGITS
     Ti
    0.42
     hi
    0.38
     RACE
    0.38
     logic
    0.36
    ぐ
    0.35
     Kec
    0.35
     nakalista
    0.34
     Hi
    0.34
     Pla
    0.34
     Logic
    0.33
    Act Density 0.094%

    No Known Activations