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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     here
    0.98
     aqui
    0.87
    here
    0.82
     यहाँ
    0.79
     вот
    0.78
     hereby
    0.76
     здесь
    0.75
     aquí
    0.75
     ici
    0.73
    这里
    0.70
    POSITIVE LOGITS
    ິ່ງ
    0.78
    subsubsection
    0.77
    <0xB3>
    0.76
     secciones
    0.75
    ###
    0.74
    ốp
    0.74
     subdivisions
    0.74
     riforma
    0.74
     ###
    0.73
    ᱼ
    0.73
    Act Density 0.522%

    No Known Activations