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

    Neuronpedia

    INDEX
    Explanations

    affirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cars
    -0.07
     diploma
    -0.07
     muss
    -0.07
    pon
    -0.06
     derecho
    -0.06
     mailing
    -0.06
    	NULL
    -0.06
    前の
    -0.06
    率
    -0.06
    ลา
    -0.06
    POSITIVE LOGITS
    ){
↵
↵
    0.08
    <Scalars
    0.06
     STORE
    0.06
     �
    0.06
    (Message
    0.06
    haled
    0.06
     galaxies
    0.06
    instanc
    0.06
     MatTable
    0.06
    __":↵
    0.06
    Act Density 0.057%

    No Known Activations