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

    Neuronpedia

    INDEX
    Explanations

    semantic versioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niejsze
    0.40
     nature
    0.38
     dom
    0.37
    verd
    0.36
     verd
    0.36
     slou
    0.36
     Trainer
    0.35
     Racine
    0.35
     Chocol
    0.35
    nature
    0.35
    POSITIVE LOGITS
    कडे
    0.43
     फॉलोइंग
    0.43
    .​​
    0.39
    otyping
    0.39
     Institutional
    0.39
    bitflag
    0.38
     সেপ্টেম্বর
    0.38
     মাহমুদ
    0.38
    上前
    0.38
    ब्दी
    0.38
    Act Density 0.001%

    No Known Activations