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

    Neuronpedia

    INDEX
    Explanations

    narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Essays
    -0.07
    pir
    -0.06
    (resultSet
    -0.06
     Mall
    -0.06
     isa
    -0.06
     Deliver
    -0.06
     Purs
    -0.06
     Moroccan
    -0.06
    可
    -0.06
    .ed
    -0.06
    POSITIVE LOGITS
     جون
    0.07
     поддерж
    0.07
    üler
    0.07
    ी,
    0.07
     Una
    0.07
    ويك
    0.07
    ома
    0.07
     goose
    0.06
    อลลาร
    0.06
     》
    0.06
    Act Density 0.055%

    No Known Activations