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

    Neuronpedia

    INDEX
    Explanations

    AWS instance types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appropriately
    -0.07
     dung
    -0.07
    iture
    -0.07
    -sup
    -0.07
     LDAP
    -0.07
     tác
    -0.06
    /open
    -0.06
     Addison
    -0.06
     ure
    -0.06
     ad
    -0.06
    POSITIVE LOGITS
    pas
    0.07
    맵
    0.07
    トラ
    0.07
    涿
    0.07
    围墙
    0.07
    Claims
    0.07
    (database
    0.07
    oba
    0.07
    动摇
    0.06
    plate
    0.06
    Act Density 0.006%

    No Known Activations