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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mêmes
    -0.69
     financières
    -0.62
     extérieures
    -0.59
     vérit
    -0.59
     hanem
    -0.59
     gouvernements
    -0.59
     createState
    -0.58
     lisäksi
    -0.57
     främ
    -0.57
     équipements
    -0.56
    POSITIVE LOGITS
     RouterModule
    0.59
     Paglinawan
    0.58
     approvals
    0.56
    хьтан
    0.56
     rou
    0.55
     allowance
    0.55
     allowances
    0.53
     approval
    0.52
     Sao
    0.51
    ebvre
    0.51
    Act Density 0.043%

    No Known Activations