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

    Neuronpedia

    INDEX
    Explanations

    texture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Input
    -0.06
    .Stat
    -0.06
     cle
    -0.06
     نبود
    -0.06
     sad
    -0.06
    につ
    -0.06
     split
    -0.06
     stuck
    -0.06
     cluster
    -0.06
    独立
    -0.06
    POSITIVE LOGITS
    0.08
     Ankara
    0.07
    영
    0.07
    Dealer
    0.07
     postponed
    0.07
     walls
    0.07
    五月
    0.06
     ≠
    0.06
    0.06
     نفت
    0.06
    Act Density 0.006%

    No Known Activations