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

    Neuronpedia

    INDEX
    Explanations

    terms related to applications and their functionalities

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

    Token followed by seemingly random text

    np_acts-logits-general · gemini-2.0-flash

    ReportGeneration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hirts
    -0.67
    )");
    -0.65
    ]--;
    -0.64
    揄
    -0.63
    Begriffsklä
    -0.63
    DeleteBehavior
    -0.62
    polation
    -0.61
    IsPostBack
    -0.61
    Ỹ
    -0.59
    pozdrawiam
    -0.58
    POSITIVE LOGITS
    ThroughAttribute
    0.65
     onAnimation
    0.63
    protoimpl
    0.60
    Obrázky
    0.55
    mybatisplus
    0.54
    _
    0.53
    ForValue
    0.52
    MigrationBuilder
    0.51
    <?>
    0.50
    mandu
    0.50
    Act Density 0.501%

    No Known Activations