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

    Neuronpedia

    INDEX
    Explanations

    web links and brand names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pl
    0.26
    As
    0.25
    Due
    0.25
    B
    0.25
    inar
    0.25
    At
    0.24
    </code>
    0.24
    T
    0.24
    IMENTAL
    0.24
    ↵
    0.24
    POSITIVE LOGITS
     老
    0.29
     кури
    0.26
    ਡੇ
    0.26
     возника
    0.26
     axioms
    0.26
     不是
    0.26
     బహి
    0.26
     Leandro
    0.25
    褐色
    0.25
     นั้น
    0.25
    Act Density 0.000%

    No Known Activations