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

    Neuronpedia

    INDEX
    Explanations

    action_input key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اتصال
    0.54
     Ди
    0.52
     egip
    0.50
     lizenz
    0.49
    Advertisement
    0.49
     طريق
    0.48
     السيد
    0.48
     अथ
    0.48
     تي
    0.48
     mecanismo
    0.48
    POSITIVE LOGITS
    ᓯ
    0.44
    ре
    0.44
    ื่อ
    0.42
    არგ
    0.41
     embraced
    0.41
     shared
    0.40
    σεων
    0.40
    FormsModule
    0.39
    )¶
    0.39
     eventually
    0.39
    Act Density 0.000%

    No Known Activations