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

    Neuronpedia

    INDEX
    Explanations

    code/debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DET
    -0.06
    �n
    -0.06
    _trees
    -0.06
     <!--
    -0.06
    KeyId
    -0.06
     май
    -0.06
     Ад
    -0.06
    _POLICY
    -0.06
    tribution
    -0.06
     yapılan
    -0.06
    POSITIVE LOGITS
     sont
    0.06
    ち
    0.06
    FieldValue
    0.06
    <Props
    0.06
    Easy
    0.06
     ban
    0.06
    encers
    0.06
    ียง
    0.06
     Reign
    0.06
     आई
    0.06
    Act Density 0.009%

    No Known Activations