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

    Neuronpedia

    INDEX
    Explanations

    ideal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цей
    -0.07
     subtree
    -0.06
    нес
    -0.06
     Pes
    -0.06
    zilla
    -0.06
     studi
    -0.06
    iska
    -0.06
     outpost
    -0.05
     strap
    -0.05
     laut
    -0.05
    POSITIVE LOGITS
    /history
    0.07
     자유
    0.07
     дат
    0.07
     perpet
    0.07
    _PARTITION
    0.06
     yapıyor
    0.06
    _IRQHandler
    0.06
     مرکزی
    0.06
    TRANSFER
    0.06
     जर
    0.06
    Act Density 0.000%

    No Known Activations