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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     жағдайда
    -0.07
    ฟรี
    -0.07
     borne
    -0.07
    చ్చు
    -0.07
    గ్య
    -0.07
     trend
    -0.07
    ર્ધ
    -0.07
    ಶ
    -0.07
    acidade
    -0.07
     descr
    -0.07
    POSITIVE LOGITS
     pinpoint
    0.12
     लाइन
    0.11
     offending
    0.10
     line
    0.10
     trecho
    0.10
     ಸಾಲ
    0.10
     lines
    0.09
     कहाँ
    0.09
     problematic
    0.09
     where
    0.09
    Act Density 0.014%

    No Known Activations