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

    Neuronpedia

    INDEX
    Explanations

    enabling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incred
    -0.07
     Remarks
    -0.07
     عوامل
    -0.06
    -enabled
    -0.06
     Prosper
    -0.06
    odings
    -0.06
     std
    -0.06
    extract
    -0.06
    omer
    -0.06
    Index
    -0.06
    POSITIVE LOGITS
    VE
    0.07
     bout
    0.06
    assi
    0.06
     :+:
    0.06
    (rr
    0.06
     spills
    0.06
     podařilo
    0.06
    inction
    0.06
    ヴ
    0.06
    ={['
    0.06
    Act Density 0.049%

    No Known Activations