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

    Neuronpedia

    INDEX
    Explanations

    conversational response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themselves
    -0.07
     Defendants
    -0.06
    フ
    -0.06
     himself
    -0.06
    readonly
    -0.06
    ملة
    -0.06
     litigation
    -0.06
     THEY
    -0.06
    рати
    -0.06
    cit
    -0.06
    POSITIVE LOGITS
    níku
    0.07
    _COST
    0.06
     порушення
    0.06
     γρα
    0.06
     Monkey
    0.06
    :";
↵
    0.06
    /page
    0.06
     قرآن
    0.06
     empleado
    0.06
     clad
    0.06
    Act Density 0.223%

    No Known Activations