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

    Neuronpedia

    INDEX
    Explanations

    hackintosh, hackathon, hack wifi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بخاری
    0.42
    rotl
    0.42
    креп
    0.41
    })\
    0.40
    ocre
    0.40
    Encoding
    0.39
    ть
    0.39
    кин
    0.39
     എടു
    0.39
     wobec
    0.39
    POSITIVE LOGITS
     hack
    1.02
     Hack
    0.97
    Hack
    0.91
     hacks
    0.89
     hacking
    0.88
     hacked
    0.75
     Hacks
    0.70
     hackers
    0.70
    hack
    0.69
     Hackett
    0.61
    Act Density 0.005%

    No Known Activations