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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ber
    -0.07
     ceremony
    -0.07
    fa
    -0.06
     succeed
    -0.06
     lemon
    -0.06
    /player
    -0.06
    })↵↵↵
    -0.06
    _instruction
    -0.06
     Milton
    -0.06
    ()}
    -0.06
    POSITIVE LOGITS
     selv
    0.07
    maal
    0.06
    .Struct
    0.06
     položky
    0.06
    /sl
    0.06
     만들
    0.06
     msgstr
    0.06
     Naples
    0.06
     hep
    0.06
    ㆍ
    0.06
    Act Density 0.007%

    No Known Activations