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

    Neuronpedia

    INDEX
    Explanations

    sports statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإ
    0.43
    кін
    0.43
    сім
    0.43
    पु
    0.42
    Strength
    0.41
     adunay
    0.41
    Catholic
    0.41
    yeh
    0.41
    లో
    0.41
    punten
    0.40
    POSITIVE LOGITS
    -
    0.48
     to
    0.41
     niente
    0.41
    0.39
     tribun
    0.38
     silicon
    0.37
    
    0.37
     interviewer
    0.37
     membranes
    0.36
     cau
    0.35
    Act Density 0.005%

    No Known Activations