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

    Neuronpedia

    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _child
    -0.07
    会展
    -0.07
     persona
    -0.07
     espos
    -0.07
    -actions
    -0.07
    nings
    -0.07
     السياسية
    -0.07
     Success
    -0.07
    _single
    -0.06
    .begin
    -0.06
    POSITIVE LOGITS
    褕
    0.07
     ))↵
    0.07
    工具
    0.07
    箍
    0.07
    .Count
    0.07
    ﲬ
    0.06
     Grape
    0.06
    ϟ
    0.06
    流行
    0.06
    硚
    0.06
    Act Density 0.021%

    No Known Activations