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

    Neuronpedia

    INDEX
    Explanations

    newest latest newest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تيجة
    0.40
    BtnPanel
    0.40
     crée
    0.38
     futile
    0.38
    蓊
    0.37
    嚧
    0.37
    BOTTOM
    0.36
    ImageUrl
    0.36
     bottoms
    0.36
    allItems
    0.36
    POSITIVE LOGITS
     latest
    0.68
    最新
    0.64
    latest
    0.62
     Latest
    0.53
     newest
    0.53
    ล่าสุด
    0.52
    最新的
    0.49
     neuesten
    0.48
    Latest
    0.48
     最新
    0.46
    Act Density 0.000%

    No Known Activations