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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桌面
    -0.07
    残酷
    -0.07
    scale
    -0.07
    沦为
    -0.07
    컥
    -0.07
    ального
    -0.07
     capped
    -0.06
     Sol
    -0.06
    🍆
    -0.06
     Dao
    -0.06
    POSITIVE LOGITS
    Remaining
    0.07
    irit
    0.07
    _ly
    0.07
     그리
    0.07
     waypoint
    0.07
    .program
    0.07
    へ
    0.06
     đợi
    0.06
    났
    0.06
     먼
    0.06
    Act Density 0.000%

    No Known Activations