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

    Neuronpedia

    INDEX
    Explanations

    must

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abhut
    0.64
     ਤੁਸੀਂ
    0.63
     интересных
    0.62
     আপনি
    0.62
    सेल
    0.62
     നല്‍
    0.60
    螳
    0.60
    এফ
    0.60
    十六章
    0.60
     તમને
    0.59
    POSITIVE LOGITS
     must
    5.63
    must
    4.95
     Must
    4.94
    Must
    4.64
     harus
    4.49
     phải
    4.39
     MUST
    4.37
    必须
    4.36
     trebuie
    4.19
     باید
    4.10
    Act Density 0.894%

    No Known Activations