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

    Neuronpedia

    INDEX
    Explanations

    projecting data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    è¹
    -0.09
     Gow
    -0.09
    tet
    -0.09
     infrared
    -0.09
     prism
    -0.09
     Medina
    -0.08
    -toast
    -0.08
    EDA
    -0.08
    izon
    -0.08
    Foto
    -0.08
    POSITIVE LOGITS
     image
    0.19
    image
    0.16
     Image
    0.14
     ill
    0.14
     diff
    0.14
     tom
    0.13
    Image
    0.13
     Shack
    0.13
     PS
    0.13
     Shannon
    0.13
    Act Density 0.032%

    No Known Activations