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

    Neuronpedia

    INDEX
    Explanations

    narrative/dramatic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     digun
    -0.09
     сто
    -0.08
     perfekt
    -0.08
     owed
    -0.08
    \/\/
    -0.07
     kutokana
    -0.07
     cir
    -0.07
     المهمة
    -0.07
     orde
    -0.07
    ოსავლ
    -0.07
    POSITIVE LOGITS
    疯
    0.09
     antics
    0.08
    _rel
    0.08
    bait
    0.08
     initiatives
    0.08
    buff
    0.08
    bungs
    0.08
     bartender
    0.07
    _BU
    0.07
     phá
    0.07
    Act Density 0.063%

    No Known Activations