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

    Neuronpedia

    INDEX
    Explanations

    episode or chapter numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ত
    0.50
     Political
    0.46
    ן
    0.46
    ষ
    0.45
    section
    0.44
    text
    0.44
    Construction
    0.44
    ৰ
    0.43
    一种
    0.42
    楍
    0.42
    POSITIVE LOGITS
     drifting
    0.49
     palais
    0.49
     monot
    0.48
     manche
    0.47
     teasing
    0.47
     wel
    0.46
     bay
    0.46
     centr
    0.45
     cré
    0.44
     rég
    0.44
    Act Density 0.001%

    No Known Activations