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

    Neuronpedia

    INDEX
    Explanations

    rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sembl
    -0.07
    وقت
    -0.07
     Nights
    -0.06
     CVS
    -0.06
     Craft
    -0.06
     bending
    -0.06
    ��
    -0.06
    ासन
    -0.06
     их
    -0.06
    ขว
    -0.06
    POSITIVE LOGITS
    омина
    0.07
    (items
    0.07
     vyk
    0.06
    adal
    0.06
     outputPath
    0.06
    assel
    0.06
    ssue
    0.06
    Clip
    0.06
     Peru
    0.06
     FLAGS
    0.06
    Act Density 0.047%

    No Known Activations