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

    Neuronpedia

    INDEX
    Explanations

    hacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mités
    0.41
    numer
    0.39
    clear
    0.39
    mité
    0.39
    பாடு
    0.38
    щего
    0.38
     AUTHORS
    0.38
    boxyl
    0.37
     mellem
    0.37
    鈐
    0.37
    POSITIVE LOGITS
     hacking
    0.79
     hack
    0.78
     hacks
    0.73
     hacked
    0.67
    Hack
    0.67
     Hacks
    0.66
     Hack
    0.65
    hack
    0.64
     hacker
    0.64
    hacking
    0.62
    Act Density 0.000%

    No Known Activations