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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acr
    -0.08
    aması
    -0.08
     murders
    -0.08
     രാത്ര
    -0.08
     trag
    -0.08
     Midnight
    -0.08
    mart
    -0.08
     قات
    -0.07
     maîtr
    -0.07
     brutal
    -0.07
    POSITIVE LOGITS
     verdere
    0.11
     дальней
    0.11
    进一步
    0.11
    ，例如
    0.10
     esimerkiksi
    0.09
     дальше
    0.09
     further
    0.09
     필요한
    0.09
     bijvoorbeeld
    0.09
    Further
    0.09
    Act Density 0.061%

    No Known Activations