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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aussi
    -0.07
    spiracy
    -0.07
    Stats
    -0.06
     durante
    -0.06
     farklı
    -0.06
    Formula
    -0.06
     Infos
    -0.06
    (Bytes
    -0.06
     ogs
    -0.06
     relevance
    -0.06
    POSITIVE LOGITS
     testing
    0.07
    óg
    0.06
     pocházet
    0.06
    uchi
    0.06
     fleets
    0.06
    .jupiter
    0.06
    	View
    0.06
     chiếc
    0.06
    腾
    0.06
    	ff
    0.06
    Act Density 0.000%

    No Known Activations