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

    Neuronpedia

    INDEX
    Explanations

    ipsum

    np_max-act · gemini-2.0-flash

    The neuron activates on common “Lorem ipsum” placeholder text (the dummy Latin filler words used in templates).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    deal
    -0.07
    Ali
    -0.07
    ůl
    -0.07
     vot
    -0.06
     ait
    -0.06
     عامل
    -0.06
    çi
    -0.06
    찰
    -0.06
     scares
    -0.06
     Manufact
    -0.06
    POSITIVE LOGITS
     Ipsum
    0.10
     ipsum
    0.09
     Paw
    0.07
     Blues
    0.07
    ,sum
    0.07
    [pos
    0.07
    SUM
    0.06
    стров
    0.06
    }elseif
    0.06
     Psalm
    0.06
    Act Density 0.000%

    No Known Activations