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

    Neuronpedia

    INDEX
    Explanations

    PDF pages and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ოვნ
    0.42
     bowled
    0.40
    solvent
    0.40
    pav
    0.39
     সম্ভবনা
    0.38
    Kenneth
    0.38
    filling
    0.38
    Bra
    0.36
    軾
    0.36
    ówno
    0.36
    POSITIVE LOGITS
     Sub
    0.45
     Resources
    0.44
    Resources
    0.43
     media
    0.41
     RESOURCES
    0.41
     apost
    0.39
     Media
    0.39
    Sub
    0.39
     pariet
    0.38
    堊
    0.38
    Act Density 0.001%

    No Known Activations