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

    Neuronpedia

    INDEX
    Explanations

    Code/document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Within
    -0.06
     colleague
    -0.06
     электри
    -0.06
    スティ
    -0.06
     мг
    -0.06
    hos
    -0.06
     کود
    -0.06
     despair
    -0.06
     trophy
    -0.06
     мистецт
    -0.06
    POSITIVE LOGITS
     Antworten
    0.08
    itorio
    0.07
    -roll
    0.07
    roll
    0.07
     Golden
    0.06
     třídy
    0.06
    portun
    0.06
    الف
    0.06
     vnode
    0.06
     Champagne
    0.06
    Act Density 0.000%

    No Known Activations