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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    亭
    -0.07
    Message
    -0.07
    Messages
    -0.06
    168
    -0.06
    PELL
    -0.06
    Disposition
    -0.06
     grassroots
    -0.06
     수도
    -0.06
    Modifiers
    -0.06
     createdAt
    -0.06
    POSITIVE LOGITS
     cabel
    0.07
     ذ
    0.07
     togg
    0.07
    \Command
    0.06
     concessions
    0.06
     MAL
    0.06
     "','"
    0.06
     وح
    0.06
     automated
    0.06
    ب
    0.05
    Act Density 0.009%

    No Known Activations