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

    Neuronpedia

    INDEX
    Explanations

    shivers down spine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τία
    -0.06
    	lib
    -0.06
     verso
    -0.06
    微笑
    -0.06
     Dict
    -0.06
     составляет
    -0.06
     răng
    -0.06
    �로
    -0.06
    تص
    -0.06
    elder
    -0.06
    POSITIVE LOGITS
     JOIN
    0.08
    _all
    0.07
    Folder
    0.07
    (man
    0.07
    ashboard
    0.07
    /edit
    0.06
    _review
    0.06
    stride
    0.06
    askell
    0.06
    ैल
    0.06
    Act Density 0.006%

    No Known Activations