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

    Neuronpedia

    INDEX
    Explanations

    approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BinaryOperation
    0.44
    零部件
    0.42
     تین
    0.41
     हल्के
    0.39
    ímav
    0.38
    现在
    0.38
     puree
    0.38
    ლების
    0.37
     cassettes
    0.37
    原因
    0.36
    POSITIVE LOGITS
     You
    0.45
     you
    0.41
     Sort
    0.40
     YouTube
    0.39
     sort
    0.39
    anks
    0.38
     Perhaps
    0.38
    you
    0.37
     Shit
    0.37
     Pro
    0.37
    Act Density 0.000%

    No Known Activations