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

    Neuronpedia

    INDEX
    Explanations

    sorry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ironic
    -0.07
     열
    -0.07
    べ
    -0.07
     लगत
    -0.06
     ofrec
    -0.06
    _auth
    -0.06
     Oscars
    -0.06
     receber
    -0.06
    -most
    -0.06
     underway
    -0.06
    POSITIVE LOGITS
    ConfigurationException
    0.07
    _JOB
    0.06
     Alliance
    0.06
    	cancel
    0.06
     minimizing
    0.06
    .Property
    0.06
    643
    0.06
    grown
    0.06
     wildfire
    0.06
     بعدی
    0.06
    Act Density 0.011%

    No Known Activations