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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tit
    -0.06
    통
    -0.06
     Bucc
    -0.06
    <Resource
    -0.06
    _AND
    -0.06
    Broken
    -0.05
     Council
    -0.05
     Kon
    -0.05
     Raf
    -0.05
    Bern
    -0.05
    POSITIVE LOGITS
     Extend
    0.07
     unravel
    0.07
     harness
    0.07
     onPostExecute
    0.07
    ısından
    0.07
     Uploaded
    0.07
     mnemonic
    0.06
     Revelation
    0.06
    PLAIN
    0.06
    ORG
    0.06
    Act Density 0.003%

    No Known Activations