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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of elite control and conspiratorial themes

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

    following "good" or implying secrets/revealing

    np_acts-logits-general · gemini-2.0-flash

    politically incorrect guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.90
    IntoConstraints
    -0.88
     समीक्षक
    -0.87
    ElementException
    -0.77
    ConstraintMaker
    -0.76
     %>%
    -0.76
     Exacts
    -0.71
    ficulties
    -0.69
    GEBURTSDATUM
    -0.69
     sherds
    -0.68
    POSITIVE LOGITS
     secret
    0.49
     sovereign
    0.48
     covert
    0.47
     icke
    0.47
    revealed
    0.47
    ровано
    0.47
     concealed
    0.46
     revelations
    0.46
    тал
    0.45
    BackColor
    0.44
    Act Density 0.623%

    No Known Activations