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

    Neuronpedia

    INDEX
    Explanations

    drop followed by specific word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যাস
    0.43
    উপ
    0.41
     पॉ
    0.41
     UP
    0.40
     Smell
    0.40
     обра
    0.40
     stamp
    0.39
     ಅನು
    0.39
     सिरे
    0.38
     Poh
    0.38
    POSITIVE LOGITS
    drop
    1.39
     Drop
    1.38
     drop
    1.33
    Drop
    1.29
    drops
    1.23
     drops
    1.23
     Dro
    1.19
    Dro
    1.18
     dropped
    1.11
     dropping
    1.10
    Act Density 0.008%

    No Known Activations