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

    Neuronpedia

    INDEX
    Explanations

    diagonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cables
    -0.07
    昇
    -0.07
    license
    -0.07
    ">{{$
    -0.07
     жит
    -0.07
    hdl
    -0.06
     shutil
    -0.06
    είς
    -0.06
     nå
    -0.06
    _seen
    -0.06
    POSITIVE LOGITS
    ►
    0.06
    vious
    0.06
    Originally
    0.06
    Tutorial
    0.06
     διά
    0.06
     situ
    0.06
     confusing
    0.06
    격
    0.06
    …..
    0.06
    .public
    0.06
    Act Density 0.003%

    No Known Activations