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

    Neuronpedia

    INDEX
    Explanations

    code loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不怕
    -0.07
     forCell
    -0.07
    シーズ
    -0.06
    Leading
    -0.06
    GreaterThan
    -0.06
    _TEMPLATE
    -0.06
    蒙
    -0.06
    START
    -0.06
    GetProperty
    -0.06
     selber
    -0.06
    POSITIVE LOGITS
    _iterations
    0.07
     pleasant
    0.07
    空中
    0.07
     getElement
    0.07
    -margin
    0.07
     Accom
    0.06
    IMATION
    0.06
    חום
    0.06
    __,
    0.06
    code
    0.06
    Act Density 0.015%

    No Known Activations