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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and parameters within technical or code-related contexts

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

    Code or data related to zeros/ones/true

    np_acts-logits-general · gemini-2.0-flash

    0 or 1, true or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %");
    -0.87
    migrationBuilder
    -0.85
    },{
    -0.79
    findpost
    -0.77
     referenties
    -0.77
    ритори
    -0.77
     */;
    -0.76
    */;
    -0.76
    !")
    -0.76
    indd
    -0.75
    POSITIVE LOGITS
     for
    0.90
     or
    0.81
     to
    0.67
     if
    0.65
     means
    0.62
     =
    0.60
     representing
    0.59
     represents
    0.57
     meaning
    0.57
     ->
    0.55
    Act Density 0.779%

    No Known Activations