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

    Neuronpedia

    INDEX
    Explanations

    on in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لتح
    -0.07
     diffuse
    -0.07
    מלי
    -0.07
    �
    -0.07
    헷
    -0.07
    建立
    -0.07
    翔
    -0.07
     shortcut
    -0.07
     way
    -0.07
    ividad
    -0.07
    POSITIVE LOGITS
    amount
    0.07
     Books
    0.07
     assh
    0.07
     moms
    0.06
    -Men
    0.06
     Tops
    0.06
     Washington
    0.06
     arasındaki
    0.06
    Sch
    0.06
    Ĝ
    0.06
    Act Density 0.326%

    No Known Activations