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

    Neuronpedia

    INDEX
    Explanations

    exclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    707
    -0.07
    708
    -0.07
     Fi
    -0.07
     sobie
    -0.06
     Beast
    -0.06
    ocuk
    -0.06
    )>=
    -0.06
     towers
    -0.06
    897
    -0.06
    988
    -0.06
    POSITIVE LOGITS
     exclus
    0.08
     excluded
    0.07
     exclude
    0.07
     exclusion
    0.07
     вак
    0.07
     excludes
    0.06
     displaced
    0.06
     Dış
    0.06
     precautions
    0.06
    EXTERNAL
    0.06
    Act Density 0.009%

    No Known Activations