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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shopping
    -0.06
    pegawai
    -0.06
     FAST
    -0.06
     Bake
    -0.06
     schedules
    -0.06
    (bus
    -0.06
    くれる
    -0.06
    .Template
    -0.06
     tube
    -0.06
    .swap
    -0.05
    POSITIVE LOGITS
     Tess
    0.07
    ACT
    0.07
     Eigen
    0.06
     taxpayers
    0.06
    ORITY
    0.06
    ает
    0.06
     mediaPlayer
    0.06
    ionic
    0.06
    чив
    0.06
    ضافة
    0.06
    Act Density 0.003%

    No Known Activations