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

    Neuronpedia

    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肩负
    -0.07
    呶
    -0.07
     asks
    -0.07
     Winners
    -0.07
     harness
    -0.07
    圭
    -0.06
     Tr
    -0.06
     selections
    -0.06
     vượt
    -0.06
    +N
    -0.06
    POSITIVE LOGITS
    哕
    0.07
    (\'
    0.07
    icial
    0.07
     "`
    0.07
     Rad
    0.06
    (detail
    0.06
    뒈
    0.06
    ;">
    0.06
    ﮐ
    0.06
     debilitating
    0.06
    Act Density 0.021%

    No Known Activations