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

    Neuronpedia

    INDEX
    Explanations

    reading next item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    變成
    0.43
    变成
    0.40
    ListName
    0.39
     বেতার
    0.39
    房价
    0.39
     resembling
    0.37
     اوپر
    0.37
    <0x9A>
    0.37
    спользова
    0.36
    证实
    0.35
    POSITIVE LOGITS
     next
    0.54
     persist
    0.42
     fais
    0.40
    これを
    0.40
    next
    0.40
     lesser
    0.39
    Next
    0.38
     persisted
    0.38
     ढेर
    0.38
     Repo
    0.38
    Act Density 0.000%

    No Known Activations