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

    Neuronpedia

    INDEX
    Explanations

    computational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abe
    -0.07
     �
    -0.06
     MADE
    -0.06
     Hogan
    -0.06
     being
    -0.06
     surgeons
    -0.06
    ."_
    -0.06
     đang
    -0.06
     spo
    -0.06
     Yer
    -0.06
    POSITIVE LOGITS
    0.07
     computational
    0.07
    0.06
     Urban
    0.06
     imprint
    0.06
    роб
    0.06
    schema
    0.06
    MENT
    0.06
    /effects
    0.06
    Classic
    0.06
    Act Density 0.006%

    No Known Activations