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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buster
    -0.08
    ma
    -0.08
     handing
    -0.07
     Map
    -0.07
     mur
    -0.07
     outputs
    -0.07
    ={}↵
    -0.07
     wood
    -0.07
     enumerator
    -0.06
     bananas
    -0.06
    POSITIVE LOGITS
     Irene
    0.07
     corruption
    0.07
     informal
    0.07
    葙
    0.07
    اجتماع
    0.07
    -io
    0.07
    丝毫不
    0.06
    火烧
    0.06
    财务管理
    0.06
    荀
    0.06
    Act Density 0.083%

    No Known Activations