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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vå
    -0.06
     Xin
    -0.06
    .frames
    -0.06
     мет
    -0.06
    İTESİ
    -0.06
     banking
    -0.06
     Seam
    -0.06
     Supreme
    -0.06
    _models
    -0.06
    лишком
    -0.05
    POSITIVE LOGITS
    -transparent
    0.07
    �프
    0.07
    .cbo
    0.07
    dictionary
    0.07
    _EVAL
    0.07
    去了
    0.07
     張
    0.07
    .HttpContext
    0.07
    ocrisy
    0.06
    loff
    0.06
    Act Density 0.002%

    No Known Activations