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

    Neuronpedia

    INDEX
    Explanations

    Code and copyright info

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arriv
    -0.07
     similarities
    -0.07
    的朋友
    -0.07
    .setStyle
    -0.07
    є
    -0.07
    相近
    -0.07
    Pdf
    -0.07
    jej
    -0.06
    ᾱ
    -0.06
    瓯
    -0.06
    POSITIVE LOGITS
    构造
    0.07
    (now
    0.07
     unconstitutional
    0.07
     Supreme
    0.07
     ||
    0.07
     TP
    0.07
     romant
    0.06
     judicial
    0.06
    Didn
    0.06
     sentenced
    0.06
    Act Density 0.037%

    No Known Activations