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

    Neuronpedia

    INDEX
    Explanations

    coding instances/objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issen
    -0.07
    'na
    -0.07
    Crop
    -0.06
     의미
    -0.06
     cpf
    -0.06
    Hide
    -0.06
    äter
    -0.06
    Truth
    -0.06
     чего
    -0.06
    の上
    -0.06
    POSITIVE LOGITS
    ักเร
    0.07
    _workflow
    0.06
     praying
    0.06
     CHtml
    0.06
     rowData
    0.06
     справж
    0.06
     Bạn
    0.06
     equip
    0.06
    ……。
    0.06
     deployment
    0.06
    Act Density 0.042%

    No Known Activations