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

    Neuronpedia

    INDEX
    Explanations

    Java version and linux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generación
    0.46
     generazione
    0.43
     generation
    0.41
    Native
    0.40
     উদ্য
    0.40
    ্যো
    0.39
     génération
    0.38
     geração
    0.38
     native
    0.37
     completion
    0.37
    POSITIVE LOGITS
    ႏ
    0.38
    iced
    0.38
     RTP
    0.37
    Mare
    0.37
    oi
    0.37
     Patriot
    0.36
     Mare
    0.36
    seab
    0.36
     चाय
    0.35
     iced
    0.35
    Act Density 0.001%

    No Known Activations