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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marion
    -0.07
     Durant
    -0.07
    -gr
    -0.07
    eu
    -0.06
    відом
    -0.06
    AIT
    -0.06
    يمة
    -0.06
    уют
    -0.06
     literally
    -0.06
    mission
    -0.06
    POSITIVE LOGITS
     katkı
    0.06
     trimming
    0.06
    [id
    0.06
     mistake
    0.06
    ((((
    0.06
     ши
    0.06
     kolay
    0.06
     Ebay
    0.06
     consenting
    0.06
    "?
    0.06
    Act Density 0.033%

    No Known Activations