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

    Neuronpedia

    INDEX
    Explanations

    essential viewing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স্পষ্ট
    0.47
     může
    0.46
    फ़ी
    0.44
    可以选择
    0.42
    ಾಗ
    0.40
     více
    0.40
     puede
    0.39
    粗
    0.38
     može
    0.38
     môže
    0.38
    POSITIVE LOGITS
     필수
    1.19
     mandatory
    1.13
     indispensable
    1.03
     indispens
    1.02
    mandatory
    1.00
     Mandatory
    1.00
     compulsory
    0.98
     obligatory
    0.96
     essential
    0.94
     essentials
    0.94
    Act Density 0.157%

    No Known Activations