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

    Neuronpedia

    INDEX
    Explanations

    overview of topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     longtime
    0.38
     amended
    0.37
     scheduled
    0.36
     Islamist
    0.36
     ہوگ
    0.35
    (':
    0.35
     '';
    0.35
     updated
    0.34
     July
    0.34
     hello
    0.33
    POSITIVE LOGITS
    Votre
    0.42
    An
    0.39
    Ed
    0.37
    ан
    0.37
    achtet
    0.37
    Lord
    0.37
     képes
    0.37
    證據
    0.36
    దే
    0.36
    Arts
    0.35
    Act Density 0.022%

    No Known Activations