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

    Neuronpedia

    INDEX
    Explanations

    hashes and keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authority
    -0.07
    =sum
    -0.07
    =pos
    -0.07
    CALLTYPE
    -0.06
     slideshow
    -0.06
    icht
    -0.06
    blend
    -0.06
    oğan
    -0.06
    má
    -0.06
    (provider
    -0.06
    POSITIVE LOGITS
     każ
    0.07
     DAO
    0.06
     ain
    0.06
    .Customer
    0.06
    ruby
    0.06
    誌
    0.06
     jewels
    0.06
     arts
    0.06
     __(
    0.06
    	finally
    0.06
    Act Density 0.016%

    No Known Activations