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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Measure
    -0.08
     enlarged
    -0.07
     thực
    -0.07
     erosion
    -0.07
    參
    -0.07
    _hierarchy
    -0.07
    ilio
    -0.07
    Requested
    -0.07
     siêu
    -0.07
    _EXTENDED
    -0.07
    POSITIVE LOGITS
    >>↵↵
    0.07
    几百
    0.07
    ware
    0.07
    ⇛
    0.06
    ナイ
    0.06
    writing
    0.06
    我们需要
    0.06
     activating
    0.06
    amina
    0.06
    elling
    0.06
    Act Density 0.000%

    No Known Activations