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

    Neuronpedia

    INDEX
    Explanations

    data structure and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    جموع
    0.44
     tụ
    0.41
     Britons
    0.41
     Groups
    0.39
     Turks
    0.37
    ಗೊಂಡ
    0.37
    <0xAA>
    0.37
    groups
    0.37
    வைய
    0.37
     skupiny
    0.36
    POSITIVE LOGITS
    وبه
    0.39
     Putt
    0.39
    puter
    0.39
    ampur
    0.39
     puts
    0.38
    SUPER
    0.38
    めっちゃ
    0.38
    も
    0.38
    Put
    0.38
    puts
    0.37
    Act Density 0.000%

    No Known Activations