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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data, specifically related to results or statistics

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.56
    DeleteBehavior
    -0.56
     *++
    -0.56
    Personendaten
    -0.54
    providedIn
    -0.54
    principalTable
    -0.53
    ]")]
    -0.53
    ChildScrollView
    -0.52
    GEBURTS
    -0.52
    PreferredItem
    -0.52
    POSITIVE LOGITS
     varones
    0.52
     mł
    0.50
     competir
    0.50
     Glaube
    0.47
     Männern
    0.47
     дів
    0.46
     masculinos
    0.46
     girls
    0.46
     Sünde
    0.46
     garçons
    0.45
    Act Density 0.011%

    No Known Activations