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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .OS
    -0.07
    ),
↵
    -0.06
     ngôi
    -0.06
    _Ptr
    -0.06
     destination
    -0.06
    的过程中
    -0.06
     toddler
    -0.06
    _UN
    -0.06
     فمن
    -0.06
    "];↵↵
    -0.06
    POSITIVE LOGITS
    自发
    0.08
     showc
    0.07
    拉升
    0.07
    高标准
    0.07
     fab
    0.07
    騙
    0.06
    _restore
    0.06
    antry
    0.06
    ཁ
    0.06
    亲手
    0.06
    Act Density 0.045%

    No Known Activations