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

    Neuronpedia

    INDEX
    Explanations

    patients and possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    limits
    -0.27
    idd
    -0.26
     devis
    -0.26
     Cout
    -0.25
    YY
    -0.25
    eler
    -0.25
     cet
    -0.25
    ×Ļ׾×Ļ
    -0.24
     puppet
    -0.24
     collect
    -0.23
    POSITIVE LOGITS
    ipline
    0.31
    ä½łçļĦ
    0.26
    éļıæŶéļıåľ°
    0.25
    ÙģÙĬد
    0.25
    èĺij
    0.25
    享åıĹåĪ°
    0.25
    缺å¸Ń
    0.25
    è¦ģ害
    0.25
    BackPressed
    0.24
     System
    0.24
    Act Density 0.002%

    No Known Activations