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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sheet
    -0.06
    CPF
    -0.06
     }}↵↵
    -0.06
     ankles
    -0.06
    щин
    -0.06
     Amber
    -0.06
     Seite
    -0.06
     LAW
    -0.06
    逸
    -0.06
    npos
    -0.06
    POSITIVE LOGITS
     adjoining
    0.07
     серед
    0.06
    ,size
    0.06
    当前
    0.06
     unbelievable
    0.06
    很多
    0.06
     stars
    0.06
     pseud
    0.06
    具有
    0.06
    且
    0.06
    Act Density 0.033%

    No Known Activations