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

    Neuronpedia

    INDEX
    Explanations

    xy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (value
    -0.07
    Resource
    -0.07
     budget
    -0.07
    :%
    -0.07
     ken
    -0.07
    /Base
    -0.07
    -score
    -0.07
     sourced
    -0.06
    沙滩
    -0.06
    個
    -0.06
    POSITIVE LOGITS
    这样一
    0.07
    シリ
    0.07
     Jakarta
    0.07
     Yapı
    0.07
     Alumni
    0.07
     Па
    0.07
    íc
    0.07
    ephir
    0.07
    .Department
    0.07
    _reordered
    0.07
    Act Density 0.004%

    No Known Activations