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

    Neuronpedia

    INDEX
    Explanations

    November 2, 2023

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tenth
    0.87
    ńca
    0.85
     ۱۹
    0.83
    冦
    0.83
    ieke
    0.81
    यें
    0.80
    ૯
    0.80
    amię
    0.79
     হুমকির
    0.77
    ዎቹ
    0.77
    POSITIVE LOGITS
    க்கி
    0.73
     Amazon
    0.70
     –
    0.64
     Historic
    0.61
     Distribution
    0.61
     per
    0.60
     ભાર
    0.60
    gra
    0.60
     land
    0.60
    ASP
    0.59
    Act Density 0.249%

    No Known Activations