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

    Neuronpedia

    INDEX
    Explanations

    choose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    剛
    -0.08
    /back
    -0.07
    ewhere
    -0.06
    _prediction
    -0.06
    _space
    -0.06
    \Domain
    -0.06
     торр
    -0.06
    ━━
    -0.06
    -return
    -0.06
     uuid
    -0.06
    POSITIVE LOGITS
    currentIndex
    0.07
    锅炉
    0.07
    LTE
    0.07
     Chavez
    0.07
    筛
    0.07
    工商联
    0.07
    GetMethod
    0.06
     timetable
    0.06
     Animation
    0.06
    教育
    0.06
    Act Density 0.002%

    No Known Activations