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

    Neuronpedia

    INDEX
    Explanations

    expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     взаим
    -0.07
     serv
    -0.07
     서버
    -0.07
    بيرة
    -0.07
    msp
    -0.06
    वर
    -0.06
    奥
    -0.06
     الض
    -0.06
    Β
    -0.06
    POSITIVE LOGITS
     odbor
    0.06
     vent
    0.06
     AC
    0.06
     //
↵
    0.06
    [^
    0.06
     Apartments
    0.06
    ضو
    0.06
     wrapper
    0.06
    ais
    0.06
     Exam
    0.06
    Act Density 0.001%

    No Known Activations