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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quot
    -0.08
    Don
    -0.07
    131
    -0.07
    00
    -0.07
    ,no
    -0.06
    10
    -0.06
    580
    -0.06
    50
    -0.06
     Don
    -0.06
     '..
    -0.06
    POSITIVE LOGITS
    _processing
    0.07
    dataType
    0.07
    ObjectContext
    0.07
    лении
    0.07
    یه
    0.06
    ΑΙ
    0.06
    icia
    0.06
    )(((
    0.06
    _CORE
    0.06
    ical
    0.06
    Act Density 0.015%

    No Known Activations