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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    因
    -0.07
    gal
    -0.07
    font
    -0.06
    ुब
    -0.06
     bona
    -0.06
     fool
    -0.06
     harms
    -0.06
     dataSet
    -0.06
     defa
    -0.06
    acket
    -0.06
    POSITIVE LOGITS
     ανα
    0.07
    Karen
    0.07
     Legal
    0.06
     unintended
    0.06
     canadian
    0.06
     Прод
    0.06
    вести
    0.06
     Psychological
    0.06
    vascular
    0.06
     Daisy
    0.06
    Act Density 0.001%

    No Known Activations