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

    Neuronpedia

    INDEX
    Explanations

    general english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Steel
    -0.07
     SPA
    -0.07
    obia
    -0.07
    роф
    -0.06
     wrapper
    -0.06
     tří
    -0.06
    심
    -0.06
     deserving
    -0.06
     Haven
    -0.06
    	timer
    -0.06
    POSITIVE LOGITS
     Ihre
    0.07
    ”，
    0.07
    Enviar
    0.07
    _wifi
    0.07
    AttributeValue
    0.07
    fant
    0.07
     Kosten
    0.07
     ApplicationContext
    0.06
    _gift
    0.06
     satisfies
    0.06
    Act Density 0.147%

    No Known Activations