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

    Neuronpedia

    INDEX
    Explanations

    rejection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _profiles
    -0.06
    ")}↵
    -0.06
    ayın
    -0.06
    ovými
    -0.06
     france
    -0.06
     vive
    -0.06
    очных
    -0.06
     t�
    -0.06
     System
    -0.06
     dara
    -0.06
    POSITIVE LOGITS
     Rever
    0.07
    _HIGH
    0.07
    Thinking
    0.06
     photos
    0.06
    LBL
    0.06
    _this
    0.06
     attend
    0.06
     بل
    0.06
    íg
    0.06
     همچنین
    0.06
    Act Density 0.002%

    No Known Activations