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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to negative impacts on life and health

    oai_token-act-pair · gemini-2.0-flash

    Changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.76
     InputDecoration
    -0.62
    IsContent
    -0.55
    DebuggerNonUser
    -0.54
    HtmlAttribute
    -0.53
    gnore
    -0.53
    ftagPool
    -0.53
    DataSnapshot
    -0.52
    jspx
    -0.52
    Искәрмәләр
    -0.52
    POSITIVE LOGITS
     births
    0.71
     releases
    0.68
     arrests
    0.63
     closures
    0.63
     detections
    0.62
     additions
    0.62
     thefts
    0.61
     transfers
    0.60
     acquisitions
    0.60
    تقاوى
    0.60
    Act Density 3.567%

    No Known Activations