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

    Neuronpedia

    INDEX
    Explanations

    giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。你
    -0.06
    uffled
    -0.06
    alette
    -0.06
     Mein
    -0.06
    sandbox
    -0.06
    actly
    -0.06
    amic
    -0.06
     sails
    -0.06
    Slave
    -0.06
     pants
    -0.06
    POSITIVE LOGITS
     wealthy
    0.07
    ходим
    0.07
    Vintage
    0.07
    udiantes
    0.07
     verbosity
    0.06
     credited
    0.06
    (jsonObject
    0.06
    liquid
    0.06
     Own
    0.06
    _Version
    0.06
    Act Density 0.001%

    No Known Activations