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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     donde
    -0.07
     сент
    -0.07
     unspecified
    -0.07
     pelos
    -0.07
    lambda
    -0.07
     مکان
    -0.07
    stable
    -0.07
     estamos
    -0.07
    保護
    -0.07
    장은
    -0.07
    POSITIVE LOGITS
     Parts
    0.07
     Signs
    0.06
     Of
    0.06
     Gear
    0.06
     CNBC
    0.06
    \">↵
    0.06
     Logical
    0.06
     })();↵
    0.06
    README
    0.06
     foreach
    0.06
    Act Density 0.009%

    No Known Activations