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

    Neuronpedia

    INDEX
    Explanations

    years from 1980 on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     통합
    -0.07
     todas
    -0.06
     تلاش
    -0.06
     Challenges
    -0.06
    англ
    -0.06
    Checkpoint
    -0.06
     всё
    -0.06
    سنگ
    -0.06
    /movie
    -0.06
    _CONTROL
    -0.06
    POSITIVE LOGITS
     skew
    0.07
     мест
    0.07
    اوي
    0.06
    .scenes
    0.06
    활
    0.06
     bil
    0.06
     jasmine
    0.06
     pruning
    0.06
     rupture
    0.06
     scm
    0.06
    Act Density 0.013%

    No Known Activations