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

    Neuronpedia

    INDEX
    Explanations

    HTML/code artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strained
    -0.06
    -town
    -0.06
     jot
    -0.06
    [j
    -0.06
     control
    -0.06
    witch
    -0.06
    \Exceptions
    -0.06
     READ
    -0.06
     densities
    -0.06
    スク
    -0.06
    POSITIVE LOGITS
     dinh
    0.07
     Martha
    0.07
     Hou
    0.07
     कट
    0.07
     Sci
    0.06
     MLM
    0.06
     Manafort
    0.06
     Pharmac
    0.06
     cevap
    0.06
    ]:=
    0.06
    Act Density 0.058%

    No Known Activations