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

    Neuronpedia

    INDEX
    Explanations

    economics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tac
    -0.07
     coz
    -0.07
    	build
    -0.06
     demok
    -0.06
    distance
    -0.06
    authority
    -0.06
    =value
    -0.06
     прибы
    -0.06
     hull
    -0.06
     jedno
    -0.06
    POSITIVE LOGITS
    olic
    0.07
     stalo
    0.06
    142
    0.06
    _EMIT
    0.06
     demonstrations
    0.06
     automotive
    0.06
    ↵
↵
↵
↵
    0.06
     mastering
    0.06
    ANNEL
    0.06
    brtc
    0.06
    Act Density 0.047%

    No Known Activations