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

    Neuronpedia

    INDEX
    Explanations

    closed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extraction
    -0.07
     warfare
    -0.07
     frustr
    -0.07
    BYTE
    -0.06
     zenith
    -0.06
    اشت
    -0.06
     Rows
    -0.06
     Peoples
    -0.06
    icode
    -0.06
    ONSE
    -0.06
    POSITIVE LOGITS
    äll
    0.07
    ASY
    0.07
     hiding
    0.06
    ATEGORY
    0.06
    (rep
    0.06
     intrigued
    0.06
    ",↵↵
    0.06
     Dodd
    0.06
    oq
    0.06
    雙
    0.06
    Act Density 0.000%

    No Known Activations