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

    Neuronpedia

    INDEX
    Explanations

    using of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avelength
    -0.07
    myp
    -0.07
    بين
    -0.07
     Dek
    -0.06
     dela
    -0.06
     Kw
    -0.06
     vim
    -0.06
    idos
    -0.06
    Honda
    -0.06
    LEM
    -0.06
    POSITIVE LOGITS
     soaring
    0.07
     плав
    0.07
     automotive
    0.07
    ización
    0.06
    achment
    0.06
    oltip
    0.06
     середови
    0.06
     Hàn
    0.06
    appen
    0.06
     Sử
    0.06
    Act Density 0.042%

    No Known Activations