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

    Neuronpedia

    INDEX
    Explanations

    80

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    To
    0.45
    আগ
    0.40
    島の
    0.39
     Среди
    0.38
     সাকিব
    0.37
     Dmitry
    0.37
    括号
    0.36
     गाड़ी
    0.36
    ToolStrip
    0.35
    希少
    0.35
    POSITIVE LOGITS
     Còn
    0.43
     interne
    0.41
     menentukan
    0.40
     còn
    0.40
     నె
    0.37
     конден
    0.37
     १७
    0.36
     Melrose
    0.36
    <0xD1>
    0.35
     auf
    0.35
    Act Density 0.043%

    No Known Activations