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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistical measures

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

    R^2^

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.90
    featureID
    -0.84
    +#+#
    -0.79
    EDEFAULT
    -0.79
    aarrggbb
    -0.79
     kaarangay
    -0.75
    setVerticalGroup
    -0.74
     defaultstate
    -0.74
     Infórmanos
    -0.73
    IntoConstraints
    -0.73
    POSITIVE LOGITS
     graças
    0.36
     París
    0.35
     thanks
    0.32
     Meski
    0.32
     Aussicht
    0.31
     wzglę
    0.31
     and
    0.31
     Trauer
    0.30
     Gründung
    0.30
     выпуска
    0.29
    Act Density 0.204%

    No Known Activations