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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     espionage
    -0.09
    фессиона
    -0.08
    \Collection
    -0.08
    进博会
    -0.07
    -par
    -0.07
    ience
    -0.07
     Stones
    -0.07
     بالإ
    -0.07
     overseeing
    -0.07
     Inspired
    -0.07
    POSITIVE LOGITS
    ################################################
    0.07
    蹲
    0.07
    �
    0.07
    :{
    0.06
    رحم
    0.06
    ,[
    0.06
    …………
    0.06
    欺
    0.06
     Login
    0.06
    .ColumnStyles
    0.06
    Act Density 0.004%

    No Known Activations