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

    Neuronpedia

    INDEX
    Explanations

    health and medical advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erto
    -0.07
    inness
    -0.07
    ade
    -0.06
     Bast
    -0.06
     precedent
    -0.06
     stringWith
    -0.06
     trabajar
    -0.06
    omu
    -0.06
    badge
    -0.06
    аного
    -0.06
    POSITIVE LOGITS
    ([\
    0.07
    лоб
    0.06
     {?>↵
    0.06
    ])->
    0.06
    (\
    0.06
     pro
    0.06
    (sheet
    0.06
    -bs
    0.06
    SupportActionBar
    0.06
     demons
    0.05
    Act Density 0.029%

    No Known Activations