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

    Neuronpedia

    INDEX
    Explanations

    words commonly used in marketing and advertising, especially for cars

    oai_token-act-pair · gemini-2.0-flash

    car interior components

    np_token-act-pair-logits · gpt-4o-mini

    car interior

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.71
     initComponents
    -0.65
     mergeFrom
    -0.64
    endphp
    -0.61
     дописавши
    -0.61
    WebVitals
    -0.60
    المشاركات
    -0.57
    ThroughAttribute
    -0.57
    #
    -0.55
     JpaRepository
    -0.54
    POSITIVE LOGITS
     console
    0.61
     dash
    0.60
     wood
    0.59
     dashboard
    0.59
    Dashboard
    0.55
     shift
    0.54
     Shift
    0.54
    wood
    0.54
    SHIFT
    0.53
     madera
    0.52
    Act Density 2.128%

    No Known Activations