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

    Neuronpedia

    INDEX
    Explanations

    workplace health risks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vscode
    -0.07
    صير
    -0.07
     Halloween
    -0.07
    勢
    -0.07
    ataloader
    -0.07
    畚
    -0.06
    人才培养
    -0.06
    我们应该
    -0.06
    多地
    -0.06
    灞
    -0.06
    POSITIVE LOGITS
     Trem
    0.08
     removes
    0.07
     Types
    0.07
    .der
    0.07
     име
    0.07
     Lamp
    0.07
     respond
    0.07
    ”).
    0.07
     Points
    0.07
     apex
    0.06
    Act Density 0.175%

    No Known Activations