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

    Neuronpedia

    INDEX
    Explanations

    physical security, first Sal, skilled driver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jarang
    0.42
    Ignore
    0.40
    昙
    0.39
    ările
    0.39
     Ignore
    0.38
     Rare
    0.38
    representing
    0.38
    inated
    0.37
    Payments
    0.37
    రిత్ర
    0.37
    POSITIVE LOGITS
     glob
    0.39
    Glob
    0.36
    LEE
    0.36
    icus
    0.35
    Cox
    0.35
    络
    0.35
     impedance
    0.35
     Habib
    0.34
     clam
    0.33
     objective
    0.33
    Act Density 0.000%

    No Known Activations