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

    Neuronpedia

    INDEX
    Explanations

    past positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theft
    -0.07
     сила
    -0.06
    лін
    -0.06
    avoid
    -0.06
     medications
    -0.06
     Зап
    -0.06
    値
    -0.06
    enses
    -0.06
    Boost
    -0.06
     قدم
    -0.05
    POSITIVE LOGITS
    --↵
    0.09
     olmuştur
    0.07
    (Screen
    0.06
    )(__
    0.06
    ่อไป
    0.06
     intercourse
    0.06
    σουν
    0.06
    ResultsController
    0.06
     arrangement
    0.06
    (Mat
    0.06
    Act Density 0.029%

    No Known Activations