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

    Neuronpedia

    INDEX
    Explanations

    Hall or house

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dag
    -0.07
     yük
    -0.06
     también
    -0.06
     addition
    -0.06
     систем
    -0.06
     japanese
    -0.06
     restart
    -0.06
     inferior
    -0.06
     Bac
    -0.06
     Brah
    -0.06
    POSITIVE LOGITS
     isinstance
    0.07
     charismatic
    0.07
     Castle
    0.07
    .getClassName
    0.07
    xDE
    0.07
    estead
    0.07
    .NotFound
    0.06
    یشن
    0.06
    Calibri
    0.06
    اطعة
    0.06
    Act Density 0.006%

    No Known Activations