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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burgers
    -0.07
     spinach
    -0.06
    察看
    -0.06
     Украины
    -0.06
     Cena
    -0.06
     жид
    -0.06
     South
    -0.06
    桧
    -0.06
     parliamentary
    -0.06
     membranes
    -0.06
    POSITIVE LOGITS
    .svg
    0.08
    拣
    0.07
    릴
    0.07
    _completed
    0.07
    Clicked
    0.07
    lator
    0.06
    מנו
    0.06
    捍
    0.06
     크게
    0.06
    ף
    0.06
    Act Density 0.013%

    No Known Activations