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

    Neuronpedia

    INDEX
    Explanations

    quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oldCount
    0.20
    ພວກ
    0.20
    售价
    0.20
     hoeveel
    0.20
     количестве
    0.19
    érapie
    0.18
     vessie
    0.18
    暱
    0.18
    量の
    0.18
     finiteness
    0.18
    POSITIVE LOGITS
     depending
    0.34
    depending
    0.28
     per
    0.26
     combined
    0.25
    per
    0.25
     dependiendo
    0.23
     Depending
    0.22
     depends
    0.22
    .
    0.22
    Depending
    0.22
    Act Density 0.082%

    No Known Activations