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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dicks
    -0.07
     cleanse
    -0.07
    IndexChanged
    -0.06
     політики
    -0.06
    Mixin
    -0.06
    уватися
    -0.06
     beurette
    -0.06
     tématu
    -0.06
    仕事
    -0.06
     inclined
    -0.06
    POSITIVE LOGITS
    ";}
    0.07
    iami
    0.06
    )"↵
    0.06
    alsy
    0.06
    _File
    0.06
    ğim
    0.06
    'ex
    0.06
     aaa
    0.06
    ention
    0.06
    ANTED
    0.06
    Act Density 0.060%

    No Known Activations