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

    Neuronpedia

    INDEX
    Explanations

    counting with total

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ï¾ĺ
    -0.10
    -0.10
     amounts
    -0.09
    328
    -0.09
     Volk
    -0.09
     Herr
    -0.09
    pto
    -0.09
     Hedge
    -0.09
    aviour
    -0.08
    etter
    -0.08
    POSITIVE LOGITS
     total
    0.38
    total
    0.28
     TOTAL
    0.23
    æĢ»
    0.23
     overall
    0.22
    _total
    0.21
    Total
    0.20
     Total
    0.19
    .total
    0.19
    -total
    0.19
    Act Density 0.096%

    No Known Activations