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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ek
    -0.07
    HEY
    -0.06
     PAS
    -0.06
     Kar
    -0.06
    乌
    -0.06
    _SIDE
    -0.06
    Х
    -0.05
     lineup
    -0.05
    ertiary
    -0.05
    まれ
    -0.05
    POSITIVE LOGITS
    คโนโลย
    0.08
    -components
    0.07
     disag
    0.07
     "*.
    0.07
     departing
    0.07
    isme
    0.07
    .DeserializeObject
    0.07
     restrictions
    0.07
    。',↵
    0.07
    .tel
    0.06
    Act Density 0.088%

    No Known Activations