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

    Neuronpedia

    INDEX
    Explanations

    references to news reporting and sources

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

    Abbreviations or acronyms

    np_acts-logits-general · gemini-2.0-flash

    news agency datelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.64
    +#+
    -0.64
     defaultstate
    -0.62
    twimg
    -0.56
     SafeMath
    -0.53
    colhead
    -0.52
    setupUi
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     dAtA
    -0.52
     &___
    -0.51
    POSITIVE LOGITS
     firmly
    0.37
     виправивши
    0.33
     Holman
    0.33
    шься
    0.33
    тесь
    0.32
     الرخصة
    0.32
     Hofmann
    0.32
     APPROPRI
    0.31
    Aholisi
    0.31
     Iglesias
    0.31
    Act Density 0.065%

    No Known Activations