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

    Neuronpedia

    INDEX
    Explanations

    primera película

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chocolat
    0.47
     contention
    0.46
     शिल्पा
    0.44
     indul
    0.43
     절대
    0.43
     piercing
    0.43
     math
    0.42
     bể
    0.41
     ஜூ
    0.41
     hotter
    0.40
    POSITIVE LOGITS
     реакции
    0.43
     образом
    0.42
    反応
    0.40
    íe
    0.40
    strnc
    0.38
    Program
    0.38
    aschen
    0.38
    ^_^
    0.37
    ate
    0.37
    ified
    0.36
    Act Density 0.002%

    No Known Activations