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

    Neuronpedia

    INDEX
    Explanations

    presentations and outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    랗
    0.33
     discredited
    0.32
    पयोग
    0.32
     demokrat
    0.32
     andRow
    0.31
    まったく
    0.31
    ७
    0.31
     moſt
    0.31
     olid
    0.31
     ด่า
    0.31
    POSITIVE LOGITS
     Information
    0.36
     L
    0.34
     G
    0.32
     H
    0.32
     Top
    0.31
     support
    0.31
     woes
    0.31
     information
    0.31
     M
    0.31
     Conference
    0.31
    Act Density 0.213%

    No Known Activations