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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nationals
    -0.07
     franchise
    -0.06
     fullname
    -0.06
     Emirates
    -0.06
    Firefox
    -0.06
    astle
    -0.06
     residual
    -0.06
    іль
    -0.06
     Realty
    -0.06
    �
    -0.05
    POSITIVE LOGITS
     can
    0.07
     ovar
    0.07
    -toast
    0.07
    +]
    0.07
     Prim
    0.07
    .SerializedName
    0.07
    (theme
    0.07
    (can
    0.07
    Contain
    0.07
     yukarı
    0.07
    Act Density 0.030%

    No Known Activations