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

    Neuronpedia

    INDEX
    Explanations

    guilt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aily
    -0.07
     meta
    -0.06
     refugee
    -0.06
     osm
    -0.06
    sville
    -0.06
     farmers
    -0.06
    格
    -0.06
    ňuje
    -0.06
     neutr
    -0.06
     plut
    -0.06
    POSITIVE LOGITS
    /blob
    0.07
     largely
    0.07
    Limited
    0.06
    	Schema
    0.06
     باعث
    0.06
     ');↵
    0.06
    ieved
    0.06
    abcdefgh
    0.06
    }`
    0.06
    »↵
    0.06
    Act Density 0.102%

    No Known Activations