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

    Neuronpedia

    INDEX
    Explanations

    legal notices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蔚来
    -0.07
    病例
    -0.07
    诹
    -0.07
    verification
    -0.07
     veh
    -0.07
     bảo
    -0.06
     Patriots
    -0.06
    金属
    -0.06
    豕
    -0.06
    告别
    -0.06
    POSITIVE LOGITS
    はない
    0.08
     Balanced
    0.07
    thest
    0.07
     Trainer
    0.07
    URRENT
    0.07
    Poss
    0.07
    onz
    0.07
    inning
    0.07
    的位置
    0.07
    (blank
    0.07
    Act Density 0.001%

    No Known Activations