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

    Neuronpedia

    INDEX
    Explanations

    choice between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mask
    -0.07
     gating
    -0.06
     Thanh
    -0.06
    .Sprintf
    -0.06
    _multip
    -0.06
    (JSONObject
    -0.06
     bụ
    -0.06
     cumshot
    -0.06
     exceeded
    -0.05
     composed
    -0.05
    POSITIVE LOGITS
    級
    0.07
    .getItems
    0.07
    販
    0.07
    .running
    0.07
    .interval
    0.07
    Hey
    0.06
     milestone
    0.06
     »,
    0.06
    �
    0.06
    _learning
    0.06
    Act Density 0.018%

    No Known Activations