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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eut
    -0.07
    Cnt
    -0.07
    Everything
    -0.06
    ведите
    -0.06
    .indent
    -0.06
    _Manager
    -0.06
    롭
    -0.06
    ेखत
    -0.06
     Jane
    -0.06
    ισμός
    -0.06
    POSITIVE LOGITS
    .m
    0.06
     Exceptions
    0.06
    initial
    0.06
     Ali
    0.06
    956
    0.06
     recall
    0.06
     tiers
    0.06
     Olson
    0.06
     Hodg
    0.06
     خویش
    0.06
    Act Density 0.016%

    No Known Activations