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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Juan
    -0.06
    ่าร
    -0.06
    мент
    -0.06
     çünkü
    -0.06
    _)
↵
    -0.06
     backwards
    -0.06
    λού
    -0.06
     حو
    -0.06
    ิญ
    -0.06
    肉
    -0.06
    POSITIVE LOGITS
    Comparator
    0.07
     donating
    0.06
     benchmarks
    0.06
     Eph
    0.06
     Pand
    0.06
     dijital
    0.06
     detainees
    0.06
     crackdown
    0.06
     descendant
    0.06
    ession
    0.06
    Act Density 0.045%

    No Known Activations