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

    Neuronpedia

    INDEX
    Explanations

    longitudinal studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     można
    -0.07
    ="">
↵
    -0.07
    uarios
    -0.07
    𫄨
    -0.07
    .Mode
    -0.06
     };
↵
    -0.06
    ⊰
    -0.06
    -bl
    -0.06
    现金
    -0.06
    enic
    -0.06
    POSITIVE LOGITS
    宽度
    0.08
    .FileSystem
    0.07
    礼仪
    0.07
     traveled
    0.07
    Activity
    0.07
    魔法师
    0.07
    tep
    0.07
     حوالي
    0.07
    ickness
    0.07
     trajectory
    0.07
    Act Density 0.057%

    No Known Activations