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

    Neuronpedia

    INDEX
    Explanations

    ching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    962
    -0.07
    danger
    -0.06
     improbable
    -0.06
    -bootstrap
    -0.06
    네
    -0.06
     resembl
    -0.06
     několik
    -0.06
     ListTile
    -0.06
    意见
    -0.06
     pillows
    -0.06
    POSITIVE LOGITS
    :H
    0.07
     testCase
    0.07
    .ejb
    0.07
    тах
    0.07
     ł
    0.07
     spoof
    0.07
     attribution
    0.06
     textual
    0.06
    (PATH
    0.06
     -,
    0.06
    Act Density 0.002%

    No Known Activations