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

    Neuronpedia

    INDEX
    Explanations

    I am or I can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کرے
    0.52
     आपने
    0.42
    feels
    0.41
     хочет
    0.40
    doesn
    0.40
     Doesn
    0.39
     Wants
    0.39
     తమ
    0.37
     Has
    0.37
    आपने
    0.37
    POSITIVE LOGITS
     am
    1.09
     myself
    0.82
     છું
    0.63
     دارم
    0.61
     हूँ
    0.59
     jsem
    0.57
     jestem
    0.54
    хожу
    0.54
     हूं
    0.54
     ام
    0.54
    Act Density 0.176%

    No Known Activations