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

    Neuronpedia

    INDEX
    Explanations

    numbered lists of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prototyping
    0.42
    మాట
    0.42
    FromNib
    0.40
    क्षणिक
    0.39
    🖥
    0.39
    截图
    0.38
    DBES
    0.38
     conclusively
    0.38
     StringIO
    0.38
    વાનું
    0.37
    POSITIVE LOGITS
    usa
    0.34
    ise
    0.34
    BM
    0.34
    odore
    0.33
     et
    0.33
    bra
    0.33
    th
    0.33
     Shakespeare
    0.33
     erm
    0.33
    мыш
    0.33
    Act Density 0.007%

    No Known Activations