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

    Neuronpedia

    INDEX
    Explanations

    biggest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुआत
    -0.06
    Anc
    -0.06
    Sparse
    -0.06
    olecule
    -0.06
    ").
    -0.06
     analyst
    -0.06
     Soap
    -0.06
    ervers
    -0.06
     "";
    -0.06
     solution
    -0.06
    POSITIVE LOGITS
     indebted
    0.07
     nek
    0.07
     lov
    0.06
     refund
    0.06
     Bil
    0.06
     emb
    0.06
     kab
    0.06
    -war
    0.06
     Türk
    0.06
     "|"
    0.06
    Act Density 0.015%

    No Known Activations