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

    Neuronpedia

    INDEX
    Explanations

    Forum/chat content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yt
    -0.06
     NL
    -0.06
     withstand
    -0.06
    année
    -0.06
    矿
    -0.06
     TM
    -0.06
     tul
    -0.06
     vọng
    -0.06
     midpoint
    -0.06
    TP
    -0.06
    POSITIVE LOGITS
     stalls
    0.07
     Bray
    0.07
    JSGlobal
    0.07
     �
    0.06
    "})↵
    0.06
     Matcher
    0.06
     pornofil
    0.06
     حف
    0.06
    iyat
    0.06
     protested
    0.06
    Act Density 0.018%

    No Known Activations