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

    Neuronpedia

    INDEX
    Explanations

    add_action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Susp
    0.44
    悬
    0.43
     susp
    0.42
     sosp
    0.41
    得出
    0.40
     подве
    0.40
     thermonuclear
    0.39
    ServerError
    0.38
    NUCLEAR
    0.38
    漱
    0.37
    POSITIVE LOGITS
    add
    0.82
     add
    0.75
    Add
    0.73
     Add
    0.72
     ADD
    0.59
     adds
    0.59
    addAction
    0.58
     添加
    0.56
     adding
    0.56
    添加
    0.55
    Act Density 0.004%

    No Known Activations