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

    Neuronpedia

    INDEX
    Explanations

    д

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inations
    -0.07
     communicated
    -0.07
    .TRAILING
    -0.06
    _CAMERA
    -0.06
     obs
    -0.06
    ULATE
    -0.06
     sharper
    -0.06
    iç
    -0.06
    кова
    -0.06
     CY
    -0.06
    POSITIVE LOGITS
    д
    0.28
    дом
    0.08
    ду
    0.08
     부
    0.08
     종
    0.07
    부
    0.07
    Д
    0.07
    де
    0.07
    (Font
    0.07
    Mrs
    0.06
    Act Density 0.004%

    No Known Activations