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

    Neuronpedia

    INDEX
    Explanations

    idea that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Typically
    0.30
    funktion
    0.29
     функции
    0.29
     สามารถ
    0.29
     Typical
    0.28
     এছাড়া
    0.28
    🩹
    0.28
    funktionen
    0.28
     расположены
    0.28
     Mainly
    0.27
    POSITIVE LOGITS
     bahwa
    0.87
     rằng
    0.79
     that
    0.74
     bahawa
    0.74
     kwamba
    0.73
    that
    0.68
     ότι
    0.68
     أنه
    0.66
    ថា
    0.63
    ว่า
    0.59
    Act Density 0.223%

    No Known Activations