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

    Neuronpedia

    INDEX
    Explanations

    online message threads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     titan
    -0.07
     doctoral
    -0.07
     Guidelines
    -0.06
     captivating
    -0.06
     Gregory
    -0.06
     lawyers
    -0.06
    Judge
    -0.06
    Whilst
    -0.06
     toc
    -0.06
     spoil
    -0.06
    POSITIVE LOGITS
    ️
    0.07
     ListViewItem
    0.06
    fontSize
    0.06
    ,),
    0.06
    (Item
    0.06
    ergency
    0.06
    edula
    0.06
     рай
    0.06
    ‪
    0.06
    ;;;
    0.06
    Act Density 0.028%

    No Known Activations