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

    Neuronpedia

    INDEX
    Explanations

    revealing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ona
    0.48
     Generally
    0.47
     अबाउट
    0.45
     Erlebnis
    0.44
     Typically
    0.43
     Difer
    0.43
     Eigen
    0.42
     Normally
    0.42
     Usually
    0.42
     volo
    0.42
    POSITIVE LOGITS
    escu
    0.40
     superstar
    0.39
     παρέ
    0.38
     tres
    0.38
    સ્ટ
    0.38
    esteem
    0.37
    Cup
    0.37
    acağız
    0.36
     আ
    0.36
    ៊
    0.36
    Act Density 0.006%

    No Known Activations