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

    Neuronpedia

    INDEX
    Explanations

    official

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    播
    -0.07
    ADDRESS
    -0.06
     işç
    -0.06
    シア
    -0.06
    chant
    -0.06
     cables
    -0.06
    Š
    -0.06
     memoria
    -0.06
     Indones
    -0.06
    stars
    -0.06
    POSITIVE LOGITS
    .remove
    0.08
     Puppy
    0.07
    nda
    0.07
    nodiscard
    0.07
     предус
    0.06
     Phys
    0.06
     herr
    0.06
    '])
↵
    0.06
    fred
    0.06
    getattr
    0.06
    Act Density 0.008%

    No Known Activations