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

    Neuronpedia

    INDEX
    Explanations

    biology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    講
    -0.07
    BEST
    -0.07
     verm
    -0.07
    _best
    -0.07
     Girls
    -0.07
    DIRECT
    -0.07
    '''↵↵
    -0.07
    )]↵
    -0.07
     thấy
    -0.07
     ド
    -0.06
    POSITIVE LOGITS
     BIOS
    0.06
    ivic
    0.06
     Benchmark
    0.06
     Decre
    0.06
    opped
    0.05
     duro
    0.05
     notifies
    0.05
    개발
    0.05
    ,type
    0.05
     마법
    0.05
    Act Density 0.109%

    No Known Activations