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

    Neuronpedia

    INDEX
    Explanations

    cc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nostru
    -0.10
     slippery
    -0.09
    /she
    -0.08
    Bur
    -0.08
     ligero
    -0.08
     سريع
    -0.08
     político
    -0.08
     extremos
    -0.07
    USTER
    -0.07
     الاحتلال
    -0.07
    POSITIVE LOGITS
     herself
    0.11
     née
    0.10
    小姐
    0.09
    anne
    0.09
     Louise
    0.09
     Margaret
    0.09
     केली
    0.08
    咪
    0.08
     стала
    0.08
     होती
    0.08
    Act Density 0.348%

    No Known Activations