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

    Neuronpedia

    INDEX
    Explanations

    multilingual contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    étés
    0.44
     असले
    0.40
    amentals
    0.39
     essentiels
    0.37
     Phần
    0.37
    ológicas
    0.37
     relacionadas
    0.37
     nisu
    0.37
     ziren
    0.37
     externes
    0.36
    POSITIVE LOGITS
     των
    0.65
    các
    0.63
     các
    0.62
     Các
    0.61
    ዎቹ
    0.61
    Các
    0.59
     delle
    0.55
    ските
    0.54
     jednotliv
    0.54
    各
    0.54
    Act Density 0.127%

    No Known Activations