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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     名
    -0.07
     Towers
    -0.07
    陸
    -0.07
    -threatening
    -0.06
     brow
    -0.06
    _platform
    -0.06
     cartridge
    -0.06
     supplied
    -0.06
    PW
    -0.06
     strom
    -0.06
    POSITIVE LOGITS
    _ak
    0.07
    _lang
    0.06
    imagenes
    0.06
    那
    0.06
    bearer
    0.06
    anean
    0.06
    Networking
    0.06
     Islam
    0.06
    Goals
    0.06
     Weiner
    0.06
    Act Density 0.000%

    No Known Activations