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

    Neuronpedia

    INDEX
    Explanations

    wanting to know you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cheery
    0.54
     wacky
    0.52
     grandpa
    0.49
     hamming
    0.48
     anthrop
    0.48
     chirop
    0.48
     nifty
    0.47
     goofy
    0.46
    deceased
    0.46
     Elderly
    0.46
    POSITIVE LOGITS
     🔥
    0.44
     damned
    0.43
    蚀
    0.42
    damn
    0.42
     vulnerabilities
    0.42
     إلي
    0.42
     gilded
    0.41
     breathless
    0.41
     damn
    0.41
     combustible
    0.40
    Act Density 0.016%

    No Known Activations