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

    Neuronpedia

    INDEX
    Explanations

    quantitative performance metrics and analysis

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

    followed by a parenthesis

    np_acts-logits-general · gemini-2.0-flash

    legal, assistance of counsel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]];
    -0.71
    PreferredItem
    -0.70
    IsPostBack
    -0.70
    ]";
    -0.65
     للاسماء
    -0.64
    IUrlHelper
    -0.63
    DockStyle
    -0.62
     esternos
    -0.62
     linkovi
    -0.61
    AutoresizingMask
    -0.61
    POSITIVE LOGITS
    TagMode
    0.55
    BufferException
    0.52
    ActionCreators
    0.52
    TargetException
    0.47
    וויק
    0.47
    apunov
    0.46
    stretchr
    0.45
    WebVitals
    0.44
    AddTagHelper
    0.44
    ftagPool
    0.43
    Act Density 25.682%

    No Known Activations