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

    Neuronpedia

    INDEX
    Explanations

    spatial arrangement and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     happenings
    0.32
     theorems
    0.28
     regimens
    0.28
     continuance
    0.28
     preacher
    0.27
     same
    0.26
     envio
    0.26
     adage
    0.26
     learnings
    0.26
     doings
    0.26
    POSITIVE LOGITS
     Aside
    0.44
     Across
    0.43
     Overall
    0.43
     Surprisingly
    0.41
     Despite
    0.40
     Several
    0.39
     Interestingly
    0.39
    全体
    0.39
     Around
    0.39
     вокруг
    0.38
    Act Density 0.016%

    No Known Activations