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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     average
    -3.13
    average
    -2.86
     Average
    -2.73
    Average
    -2.70
     AVERAGE
    -2.25
    AVERAGE
    -2.08
     promedio
    -2.02
     avg
    -1.98
     durchschnitt
    -1.93
    avg
    -1.86
    POSITIVE LOGITS
     of
    0.66
    ,
    0.59
     (
    0.52
     and
    0.50
     
    0.50
     –
    0.49
     et
    0.48
    -
    0.46
     person
    0.46
     T
    0.45
    Act Density 0.135%

    No Known Activations