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

    Neuronpedia

    INDEX
    Explanations

    Relationships and interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    äºĴ
    -0.34
     inter
    -0.31
     exchanging
    -0.30
    äºĴ缸
    -0.30
    تبادÙĦ
    -0.26
    ä¸Ĭä¸ĭ游
    -0.26
    alia
    -0.26
    ãģĬäºĴãģĦ
    -0.26
    _Statics
    -0.25
     PaÅĦst
    -0.25
    POSITIVE LOGITS
    对åºĶ
    0.29
     Correspond
    0.29
     correspond
    0.26
     conduct
    0.26
     histor
    0.25
    对åºĶçļĦ
    0.25
     corres
    0.25
     correspondence
    0.25
     membership
    0.24
    ULSE
    0.24
    Act Density 0.007%

    No Known Activations