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

    Neuronpedia

    INDEX
    Explanations

    premium listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /.
    0.77
     lowercase
    0.75
    iral
    0.72
    lowercase
    0.70
    isia
    0.69
    _->
    0.69
    overe
    0.68
    pie
    0.67
    anean
    0.66
    arya
    0.66
    POSITIVE LOGITS
    condensation
    0.69
     eTo
    0.68
     pom
    0.68
     Textiles
    0.67
     Нет
    0.66
    Ligações
    0.64
     ባ
    0.63
    ज्योति
    0.63
     বাড়
    0.62
     ге
    0.62
    Act Density 0.000%

    No Known Activations