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

    Neuronpedia

    INDEX
    Explanations

    something followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.63
     ጡ
    0.61
    謁
    0.61
    rophys
    0.61
     sintered
    0.60
    ્યાં
    0.59
    է
    0.59
    ోధ
    0.59
    Quién
    0.57
     poached
    0.57
    POSITIVE LOGITS
     конструкции
    0.64
     लिखित
    0.60
    奉
    0.59
    जैसा
    0.58
     About
    0.56
    about
    0.55
    ist
    0.54
     Missing
    0.54
     గురించి
    0.54
    timestamps
    0.54
    Act Density 0.005%

    No Known Activations