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

    Neuronpedia

    INDEX
    Explanations

    irt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卫生间
    -0.07
     SIZE
    -0.07
    ASCII
    -0.07
     rails
    -0.07
     обесп
    -0.07
    寝
    -0.07
    树枝
    -0.07
     Fuji
    -0.07
    ✮
    -0.07
    DialogTitle
    -0.07
    POSITIVE LOGITS
    .rotation
    0.07
     Nab
    0.07
    forgettable
    0.07
     Bolt
    0.07
    ব
    0.07
    слав
    0.06
    (payment
    0.06
    entence
    0.06
     degrees
    0.06
    ꦩ
    0.06
    Act Density 0.066%

    No Known Activations