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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exclusivo
    -0.07
    巧
    -0.07
     వెల్ల
    -0.07
     Exclusive
    -0.07
     감사
    -0.07
     exclusivos
    -0.07
    Exclusive
    -0.07
     quantified
    -0.07
     दर्द
    -0.07
    urator
    -0.07
    POSITIVE LOGITS
     Datagram
    0.09
     wahi
    0.08
     difusión
    0.08
    (go
    0.08
     annonces
    0.08
    ज्ञ
    0.08
    >>();↵
    0.08
    >Hello
    0.08
     Whois
    0.08
     enlaces
    0.08
    Act Density 0.004%

    No Known Activations