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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Territory
    -0.06
     crust
    -0.06
     hos
    -0.06
    901
    -0.06
     sunlight
    -0.06
     đặt
    -0.06
     Computing
    -0.06
     wrist
    -0.06
     щодо
    -0.06
     sandwich
    -0.05
    POSITIVE LOGITS
    ораз
    0.07
     соот
    0.07
    وان
    0.07
    boards
    0.07
    チャ
    0.07
    hf
    0.06
    委员会
    0.06
    στε
    0.06
     Bron
    0.06
     Naruto
    0.06
    Act Density 0.071%

    No Known Activations