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

    Neuronpedia

    INDEX
    Explanations

    George W. Bush

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grading
    -0.07
     surprised
    -0.06
    瞬
    -0.06
    _write
    -0.06
    voří
    -0.06
    .Tipo
    -0.06
    DEFINED
    -0.06
     cour
    -0.06
     Literature
    -0.06
    Cho
    -0.06
    POSITIVE LOGITS
    .pth
    0.07
    ='"+
    0.06
     mrt
    0.06
     м
    0.06
     особлив
    0.06
     qq
    0.06
     apoptosis
    0.06
    rops
    0.06
     ppm
    0.06
    県
    0.06
    Act Density 0.019%

    No Known Activations