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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.98
    ,
    0.84
    0.83
     (
    0.82
    ↵
    0.81
     *
    0.81
     that
    0.80
     a
    0.79
     some
    0.79
    .
    0.78
    POSITIVE LOGITS
     králov
    0.57
    خستان
    0.57
    ißler
    0.55
    arrerol
    0.55
     кеңсеси
    0.54
    abhuto
    0.54
    والفقار
    0.52
     কিরূপে
    0.52
    atthaya
    0.52
    ananti
    0.51
    Act Density 0.494%

    No Known Activations