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

    Neuronpedia

    INDEX
    Explanations

    Why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _retry
    -0.06
    didn
    -0.06
     Pav
    -0.06
     الدول
    -0.06
     Can
    -0.06
    lr
    -0.06
     Powder
    -0.06
    gran
    -0.06
    eday
    -0.06
     psychologists
    -0.06
    POSITIVE LOGITS
     ########.
    0.07
     Finals
    0.07
    امي
    0.07
    ản
    0.07
     ><
    0.07
    emp
    0.06
     MI
    0.06
     staunch
    0.06
     toolbox
    0.06
    τύ
    0.06
    Act Density 0.003%

    No Known Activations