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

    Neuronpedia

    INDEX
    Explanations

    one item per slot restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uel
    -0.08
     כשה
    -0.08
     jaarlijkse
    -0.08
    -yellow
    -0.08
    uelos
    -0.07
    ua
    -0.07
     jaarlijks
    -0.07
     topl
    -0.07
    fully
    -0.07
     regular
    -0.07
    POSITIVE LOGITS
     aconsel
    0.09
     समान
    0.09
     preventing
    0.08
    Prevent
    0.08
     предотвращ
    0.08
     чул
    0.08
     deciso
    0.08
     prevented
    0.08
     prevent
    0.08
     conselho
    0.08
    Act Density 0.007%

    No Known Activations