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

    Neuronpedia

    INDEX
    Explanations

    open to discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stars
    0.82
    <img>
    0.76
     Stars
    0.75
    Inserting
    0.75
    IT
    0.70
    entering
    0.69
    copied
    0.69
    шов
    0.68
     இன்னொரு
    0.68
    esc
    0.67
    POSITIVE LOGITS
    тету
    0.85
     predictions
    0.79
     prediction
    0.79
     ಎಲ್ಲಾ
    0.78
     allez
    0.77
     apps
    0.76
     periods
    0.76
     nominees
    0.76
    ,)
    0.75
     asses
    0.75
    Act Density 0.000%

    No Known Activations