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

    Neuronpedia

    INDEX
    Explanations

    code or technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    улю
    -0.08
    iday
    -0.07
    ưng
    -0.07
     тогда
    -0.06
    ιστή
    -0.06
     sexe
    -0.06
    _sessions
    -0.06
    _record
    -0.06
    ümüz
    -0.06
    人员
    -0.06
    POSITIVE LOGITS
     SSL
    0.07
     "+↵
    0.07
    <ID
    0.06
     JSON
    0.06
    \<^
    0.06
    uch
    0.06
     Enhanced
    0.06
    (initial
    0.06
     псих
    0.06
     fallback
    0.06
    Act Density 0.000%

    No Known Activations