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

    Neuronpedia

    INDEX
    Explanations

    prop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     América
    -0.07
     University
    -0.07
     railway
    -0.07
     unterstüt
    -0.07
     cancer
    -0.06
     danger
    -0.06
    číta
    -0.06
     Yun
    -0.06
    _Delay
    -0.06
    Center
    -0.06
    POSITIVE LOGITS
     prop
    0.11
     Prop
    0.11
     Props
    0.10
    prop
    0.10
    Prop
    0.09
     props
    0.09
    (props
    0.09
    PROP
    0.09
    (prop
    0.08
     proprietor
    0.08
    Act Density 0.025%

    No Known Activations