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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цион
    -0.07
    pired
    -0.07
    τομα
    -0.07
     صنایع
    -0.06
    ær
    -0.06
     chấp
    -0.06
     нер
    -0.06
    ','','
    -0.06
    _favorite
    -0.06
    ev
    -0.06
    POSITIVE LOGITS
     citation
    0.07
     drum
    0.07
     ".$
    0.07
     warp
    0.06
     scopes
    0.06
     +=
    0.06
    Ont
    0.06
    }'.
    0.06
    asc
    0.06
     judgment
    0.06
    Act Density 0.179%

    No Known Activations