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

    Neuronpedia

    INDEX
    Explanations

    strategy in various applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اً
    1.03
    AI
    0.97
    的
    0.97
    YA
    0.96
    S
    0.96
    কে
    0.95
    ene
    0.92
    人
    0.88
    sey
    0.87
    ot
    0.87
    POSITIVE LOGITS
     dismin
    1.36
     ambas
    1.35
     возмо
    1.34
     algunas
    1.29
     equipos
    1.28
     estrategia
    1.23
     presentes
    1.20
     quím
    1.19
     crít
    1.19
     estrategias
    1.18
    Act Density 0.022%

    No Known Activations