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

    Neuronpedia

    INDEX
    Explanations

    `.js` files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parallels
    0.53
     purpose
    0.52
    却
    0.51
    paration
    0.51
    卻
    0.51
    Charting
    0.50
     granular
    0.48
    द्दी
    0.48
    却是
    0.47
     unbiased
    0.46
    POSITIVE LOGITS
    ˆ
    0.58
    <unused2105>
    0.58
     "/"
    0.57
     calcS
    0.57
     Yer
    0.57
    Yer
    0.56
     Leistungen
    0.56
     numquam
    0.56
     Ned
    0.55
    0.55
    Act Density 0.067%

    No Known Activations