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

    Neuronpedia

    INDEX
    Explanations

    specific structural and formal elements in the text

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

    Text before periods or semicolons

    np_acts-logits-general · gemini-2.0-flash

    critical, enough, further, family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    -0.78
     läßt
    -0.74
    this
    -0.70
    we
    -0.70
    让我们
    -0.67
    !!!
    -0.64
    This
    -0.63
    I
    -0.63
    "!
    -0.63
    !"
    -0.62
    POSITIVE LOGITS
    دانشنامهٔ
    0.85
    tdessen
    0.77
    /**
    0.73
     AssemblyTitle
    0.73
    ViewImports
    0.73
    principalColumn
    0.72
    SPATH
    0.72
     Sebab
    0.71
     виправивши
    0.69
     ?>>
    0.69
    Act Density 0.103%

    No Known Activations