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

    Neuronpedia

    INDEX
    Explanations

    Audits and reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOCAL
    -0.08
     alternatively
    -0.07
    reak
    -0.06
    ifié
    -0.06
    組織
    -0.06
     furry
    -0.06
     Diamonds
    -0.06
    -z
    -0.06
     university
    -0.06
     Corpor
    -0.06
    POSITIVE LOGITS
     María
    0.07
    ΑΤ
    0.06
     geometric
    0.06
    는
    0.06
     individ
    0.06
     Vintage
    0.06
    เคราะห
    0.06
    	person
    0.06
    _BLUE
    0.06
    	sql
    0.06
    Act Density 0.030%

    No Known Activations