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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	col
    -0.07
     Dün
    -0.07
     vše
    -0.07
     hvor
    -0.06
     doping
    -0.06
     unve
    -0.06
     Heads
    -0.06
     desi
    -0.06
    _PKT
    -0.06
     sk
    -0.06
    POSITIVE LOGITS
     Guides
    0.07
    _likelihood
    0.06
     guide
    0.06
    _ED
    0.06
    PHONE
    0.06
     getInfo
    0.06
    acious
    0.06
     Eleanor
    0.06
    uky
    0.06
    實
    0.06
    Act Density 0.017%

    No Known Activations