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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by parentheses or links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ses
    0.77
    SMS
    0.76
    formas
    0.71
     चाँ
    0.70
    Ether
    0.68
    TikTok
    0.68
     telefoon
    0.67
     mannit
    0.67
    tig
    0.67
     түр
    0.65
    POSITIVE LOGITS
     info
    1.30
    info
    1.26
     Info
    1.08
     hello
    1.03
     sales
    0.99
    INFO
    0.93
     INFO
    0.92
     hola
    0.92
    Info
    0.91
    hello
    0.91
    Act Density 0.093%

    No Known Activations