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

    Neuronpedia

    INDEX
    Explanations

    introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     черво
    0.48
    evol
    0.47
    ᄇ
    0.47
     ಅಥವಾ
    0.46
    ब्रिट
    0.46
    cached
    0.45
    ก่อ
    0.45
     قوان
    0.45
    verhalten
    0.45
    ٸ
    0.44
    POSITIVE LOGITS
     myArray
    0.45
     as
    0.44
     Foundation
    0.44
     Ah
    0.43
     Bon
    0.41
     interesting
    0.40
     Chain
    0.40
     all
    0.40
     nerdy
    0.40
     Merry
    0.39
    Act Density 0.001%

    No Known Activations