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

    Neuronpedia

    INDEX
    Explanations

    multilingual numbers and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ments
    1.70
    en
    1.61
    на
    1.58
    em
    1.54
    льные
    1.52
    ο
    1.50
    туры
    1.49
    ন
    1.46
        
    1.43
    ဣ
    1.42
    POSITIVE LOGITS
     kobi
    1.40
    ्यातील
    1.32
     luisant
    1.32
     procédés
    1.30
     prossima
    1.28
     povez
    1.27
     jaunâtre
    1.27
     strumento
    1.23
     jardin
    1.22
     selezione
    1.22
    Act Density 0.083%

    No Known Activations