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

    Neuronpedia

    INDEX
    Explanations

    code/configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faction
    -0.08
    艺术
    -0.07
     Sid
    -0.07
     Vij
    -0.07
     Emily
    -0.06
     intermedi
    -0.06
     是否
    -0.06
    iała
    -0.06
    肢体
    -0.06
     Candid
    -0.06
    POSITIVE LOGITS
    利用率
    0.07
    *******
    0.07
     Ar
    0.07
     Honour
    0.07
    小康社会
    0.07
     decoded
    0.07
     intercepted
    0.07
    datos
    0.06
    лав
    0.06
     Listen
    0.06
    Act Density 0.112%

    No Known Activations