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

    Neuronpedia

    INDEX
    Explanations

    ------

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Unsupported
    -0.07
    .Ο
    -0.06
    ffmpeg
    -0.06
     страны
    -0.06
    pk
    -0.05
    macen
    -0.05
     blocker
    -0.05
     гер
    -0.05
     Café
    -0.05
    iffany
    -0.05
    POSITIVE LOGITS
    Atoms
    0.08
    ку
    0.07
     ********************************************************
    0.07
    ]?
    0.07
    abbreviation
    0.07
    昭和
    0.07
    *)↵
    0.07
    alcon
    0.07
     cuts
    0.07
     Nut
    0.07
    Act Density 0.002%

    No Known Activations