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

    Neuronpedia

    INDEX
    Explanations

    complaint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEC
    -0.07
     seguridad
    -0.07
     jazy
    -0.07
     freedom
    -0.07
    ur
    -0.07
     access
    -0.07
     EUR
    -0.06
    Knowledge
    -0.06
     نیرو
    -0.06
     erre
    -0.06
    POSITIVE LOGITS
     complaint
    0.12
     complaints
    0.12
     complain
    0.12
     complaining
    0.11
     complains
    0.11
     complained
    0.10
     Complaint
    0.09
    plaint
    0.08
    Comparator
    0.07
     Chen
    0.07
    Act Density 0.008%

    No Known Activations