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

    Neuronpedia

    INDEX
    Explanations

    mitigating negative impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .integration
    -0.08
     búsqueda
    -0.07
     Truy
    -0.07
     parametros
    -0.06
     returned
    -0.06
    ống
    -0.06
    سد
    -0.06
    ければ
    -0.06
     kos
    -0.06
     شی
    -0.06
    POSITIVE LOGITS
     rallying
    0.07
     Cler
    0.06
    .super
    0.06
     blame
    0.06
     break
    0.06
     doc
    0.06
     Arbit
    0.06
     disabilities
    0.06
    IndexChanged
    0.06
    ounge
    0.06
    Act Density 0.064%

    No Known Activations