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

    Neuronpedia

    INDEX
    Explanations

    offer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рус
    -0.07
    JECT
    -0.07
     themselves
    -0.07
    -0.06
     daddy
    -0.06
     vũ
    -0.06
    placement
    -0.06
     Percy
    -0.06
     visited
    -0.06
     neat
    -0.06
    POSITIVE LOGITS
    对于
    0.07
    (sd
    0.06
    relative
    0.06
    (coeff
    0.06
    .sender
    0.06
    .jquery
    0.06
    配置
    0.06
    ↵
↵
↵
↵
    0.06
     �
    0.06
     оцен
    0.06
    Act Density 0.038%

    No Known Activations