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

    Neuronpedia

    INDEX
    Explanations

    SQL schema definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nutrients
    0.39
     hydrolyzed
    0.39
    沨
    0.38
     любых
    0.38
    Benzyloxy
    0.38
     наличии
    0.37
     territoires
    0.37
    ddagger
    0.37
     ஊற
    0.37
    থাৎ
    0.37
    POSITIVE LOGITS
     ,
    0.54
    ,
    0.48
     '',
    0.46
    ，
    0.42
    ،
    0.42
    D
    0.42
     ،
    0.41
    ],
    0.38
     DISABLE
    0.38
    >,
    0.38
    Act Density 0.006%

    No Known Activations