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

    Neuronpedia

    INDEX
    Explanations

    Logic, seamless, TLS, Contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    0.59
    خ
    0.59
    يت
    0.54
     consultancy
    0.47
    メーカー
    0.47
     fonction
    0.47
    ه
    0.47
    كان
    0.46
    मा
    0.46
     WARRANTY
    0.45
    POSITIVE LOGITS
     exorbitant
    0.51
     upd
    0.49
     чтоб
    0.49
    ưở
    0.48
     Up
    0.47
    न्नई
    0.47
    upa
    0.46
     rus
    0.46
    upe
    0.46
    rus
    0.45
    Act Density 0.001%

    No Known Activations