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

    Neuronpedia

    INDEX
    Explanations

    Sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    origin
    -0.06
     pošk
    -0.06
    heart
    -0.06
     söy
    -0.06
     být
    -0.06
     عليه
    -0.06
     telefon
    -0.06
    imer
    -0.06
     ý
    -0.06
     яр
    -0.06
    POSITIVE LOGITS
    箱
    0.06
     Bath
    0.06
     IMPLIED
    0.06
     Swedish
    0.06
    ictionary
    0.06
    aspberry
    0.06
     HashSet
    0.06
     Wrestling
    0.06
    wow
    0.06
     Cent
    0.06
    Act Density 0.002%

    No Known Activations