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

    Neuronpedia

    INDEX
    Explanations

    drive-thru operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.64
    ρου
    0.63
    ολ
    0.59
    ων
    0.57
    ou
    0.56
    ικ
    0.56
    ري
    0.55
     Sicherheits
    0.54
     keamanan
    0.54
     dwa
    0.54
    POSITIVE LOGITS
     ও
    0.55
    LLO
    0.54
    STAN
    0.54
     отдельно
    0.54
    ljenje
    0.53
    ADY
    0.52
    testX
    0.52
     перспек
    0.51
    śmy
    0.50
    ᡤ
    0.50
    Act Density 0.002%

    No Known Activations