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

    Neuronpedia

    INDEX
    Explanations

    code expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiempo
    -0.07
    AVED
    -0.07
    (ticket
    -0.07
    Monitor
    -0.06
     federation
    -0.06
    -hearted
    -0.06
    انیا
    -0.06
    .arguments
    -0.06
    '
    -0.06
    buch
    -0.06
    POSITIVE LOGITS
     군
    0.07
     gent
    0.07
    感觉
    0.07
     Chlor
    0.06
    (strpos
    0.06
     Av
    0.06
     Canberra
    0.06
    ouns
    0.06
     redhead
    0.06
    (Il
    0.06
    Act Density 0.002%

    No Known Activations