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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irut
    -0.07
    relationships
    -0.07
    tributes
    -0.07
     unlawful
    -0.06
    .xxx
    -0.06
     tedbir
    -0.06
     municipalities
    -0.06
    ادات
    -0.06
     tụ
    -0.06
    ですが
    -0.06
    POSITIVE LOGITS
     """.
    0.07
    """.
    0.07
     */}↵
    0.06
    **/↵
    0.06
    ":-
    0.06
     handleChange
    0.06
    }*/↵
    0.06
    DMETHOD
    0.06
    ={()
    0.06
    Inv
    0.06
    Act Density 0.000%

    No Known Activations