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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stra
    -0.07
    ービ
    -0.07
    dra
    -0.07
     colossal
    -0.07
    되었다
    -0.06
    mas
    -0.06
     různé
    -0.06
     пап
    -0.06
     olig
    -0.06
    ằ
    -0.06
    POSITIVE LOGITS
     }:
    0.06
     acknowledges
    0.06
    [np
    0.06
    ,right
    0.06
    }$/
    0.06
     İşte
    0.06
     partners
    0.06
    یک
    0.06
     conse
    0.06
    web
    0.06
    Act Density 0.001%

    No Known Activations