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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лютого
    -0.07
     Marian
    -0.07
    Mor
    -0.06
    Marg
    -0.06
    nesty
    -0.06
     оч
    -0.06
     reconciliation
    -0.06
    ุตสาหกรรม
    -0.06
    argar
    -0.06
     defensive
    -0.06
    POSITIVE LOGITS
    _ul
    0.07
    aturing
    0.06
     قدرت
    0.06
    -uri
    0.06
    
    0.06
    )])
    0.06
    !!
    0.06
    _parents
    0.06
    uctose
    0.06
     Buckingham
    0.06
    Act Density 0.033%

    No Known Activations