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

    Neuronpedia

    INDEX
    Explanations

    AAAAAAAA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newborn
    -0.06
     skincare
    -0.06
     pursuits
    -0.06
     Prize
    -0.06
     legendary
    -0.06
    anny
    -0.05
     �
    -0.05
     embrace
    -0.05
    ÓN
    -0.05
     autoimmune
    -0.05
    POSITIVE LOGITS
    ικών
    0.07
    困
    0.07
    Installing
    0.07
     authenticated
    0.07
     drained
    0.07
    .createElement
    0.07
     》
    0.07
    ными
    0.07
    441
    0.07
     stern
    0.07
    Act Density 0.001%

    No Known Activations