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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рес
    -0.07
     rebate
    -0.07
    _POP
    -0.07
    _publish
    -0.06
     onResume
    -0.06
     repr
    -0.06
     franchises
    -0.06
    aktu
    -0.06
    _VERTEX
    -0.06
     pud
    -0.06
    POSITIVE LOGITS
    ์,
    0.07
     elemental
    0.07
     výj
    0.07
    HL
    0.06
     juste
    0.06
     đủ
    0.06
     황
    0.06
    &T
    0.06
     '">'
    0.06
     Ге
    0.06
    Act Density 0.045%

    No Known Activations