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

    Neuronpedia

    INDEX
    Explanations

    observation followed by experiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不过
    -0.07
     třeba
    -0.06
    elight
    -0.06
    arest
    -0.06
    .д
    -0.06
     söyledi
    -0.06
    фра
    -0.06
     Tiểu
    -0.06
    ůj
    -0.06
     Ones
    -0.06
    POSITIVE LOGITS
    _proto
    0.07
    .
↵
↵
    0.07
    0.06
    ()},↵
    0.06
     deleting
    0.06
     columnName
    0.06
    zed
    0.06
    "},↵
    0.06
     extracted
    0.06
     كن
    0.06
    Act Density 0.028%

    No Known Activations