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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coop
    -0.06
    Domin
    -0.06
    _CLIP
    -0.06
    목
    -0.06
    اختی
    -0.06
     Shack
    -0.06
     Dense
    -0.06
     شکن
    -0.06
    关键
    -0.06
     스트
    -0.06
    POSITIVE LOGITS
     infinit
    0.07
    'S
    0.07
     Representatives
    0.07
    )));↵
    0.07
    .?
    0.07
     Qu
    0.07
    Include
    0.07
    ])));↵
    0.07
     fals
    0.06
     věc
    0.06
    Act Density 0.011%

    No Known Activations