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

    Neuronpedia

    INDEX
    Explanations

    stage names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foy
    -0.07
    초
    -0.06
    .bb
    -0.06
     imz
    -0.06
     schwer
    -0.06
    .gender
    -0.06
    Des
    -0.06
     Zombies
    -0.06
     Pace
    -0.06
    碰
    -0.06
    POSITIVE LOGITS
    εξ
    0.07
    evaluate
    0.07
    つけ
    0.06
     لق
    0.06
    ائج
    0.06
     oto
    0.06
    omin
    0.06
    ',['../
    0.06
    osal
    0.06
    _Local
    0.06
    Act Density 0.024%

    No Known Activations