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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unlaw
    -0.09
     զարգացման
    -0.08
    чун
    -0.08
     ösdür
    -0.08
     ուսումնասիր
    -0.08
     harum
    -0.08
     আনন্দ
    -0.08
     ഇയ
    -0.08
     колдон
    -0.08
    નલ
    -0.08
    POSITIVE LOGITS
     categories
    0.08
    Ω
    0.08
     sequences
    0.08
    "x
    0.07
    "K
    0.07
    Omega
    0.07
     trains
    0.07
    输入
    0.07
     entries
    0.07
     entradas
    0.07
    Act Density 0.001%

    No Known Activations