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

    Neuronpedia

    INDEX
    Explanations

    EVs or cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сора
    0.45
    。"
    0.40
     promulgate
    0.38
     corne
    0.37
    േയ
    0.36
    )|$(
    0.36
    ဲ
    0.35
     monadic
    0.35
    िता
    0.35
    सीना
    0.35
    POSITIVE LOGITS
     Mighty
    0.41
     Ice
    0.41
     Merced
    0.41
     Ghost
    0.40
     House
    0.40
    ٨
    0.40
     Amph
    0.39
     hordes
    0.39
     Motorsport
    0.38
     M
    0.38
    Act Density 0.030%

    No Known Activations