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

    Neuronpedia

    INDEX
    Explanations

    questions asking which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dataIn
    0.48
    illustrations
    0.47
    ଛି
    0.46
     investimento
    0.46
    dbox
    0.45
    Fuse
    0.43
    myTransform
    0.42
    illustration
    0.42
    োনাল
    0.41
     দাত
    0.41
    POSITIVE LOGITS
     முதல்
    0.42
    0.41
     whining
    0.40
     claimant
    0.39
     thing
    0.38
     wh
    0.38
     [
    0.38
     Firstly
    0.38
    のに
    0.38
     ①
    0.38
    Act Density 0.001%

    No Known Activations