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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安装
    -0.07
     Kansas
    -0.07
    ilenames
    -0.07
     из
    -0.06
    �
    -0.06
    .uc
    -0.06
     наход
    -0.06
     Manus
    -0.06
     horns
    -0.06
     thickness
    -0.06
    POSITIVE LOGITS
    ่อย
    0.07
    */,↵
    0.06
    +x
    0.06
    chine
    0.06
     fif
    0.06
    nginx
    0.06
     note
    0.06
    811
    0.06
    STREAM
    0.06
    iphers
    0.06
    Act Density 0.000%

    No Known Activations