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

    Neuronpedia

    INDEX
    Explanations

    hacking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OUT
    -0.07
     Christoph
    -0.07
    orneys
    -0.07
     presenta
    -0.07
    'O
    -0.07
     Cair
    -0.06
     bez
    -0.06
     Reef
    -0.06
    NSURL
    -0.06
    +B
    -0.06
    POSITIVE LOGITS
     Hack
    0.11
     hack
    0.09
     hacked
    0.07
     hacking
    0.07
     hacks
    0.07
    Hack
    0.07
     حک
    0.07
     Security
    0.07
    hack
    0.07
     واج
    0.07
    Act Density 0.005%

    No Known Activations