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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plut
    -0.09
    ulum
    -0.09
     rav
    -0.08
    romen
    -0.07
     Dolby
    -0.07
    avar
    -0.07
     peregr
    -0.07
     rushing
    -0.07
     ****************************************************************
    -0.07
     elenco
    -0.07
    POSITIVE LOGITS
    ’action
    0.08
     भन
    0.08
     oqa
    0.08
     कही
    0.08
     wees
    0.08
     makers
    0.08
    -makers
    0.07
     હો
    0.07
     भन्दा
    0.07
    小姐
    0.07
    Act Density 0.053%

    No Known Activations