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

    Neuronpedia

    INDEX
    Explanations

    conditions and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anon
    0.42
     студен
    0.42
    жении
    0.41
     சர்வதேச
    0.41
    InitFlag
    0.40
     voluptate
    0.39
    のでしょうか
    0.39
    embryon
    0.39
    rzym
    0.38
     Anon
    0.38
    POSITIVE LOGITS
     patt
    0.39
    AYA
    0.38
     factors
    0.38
     dangers
    0.38
     overlays
    0.38
     SELL
    0.37
     planters
    0.36
     storms
    0.36
    스럽
    0.36
     RELATED
    0.35
    Act Density 0.000%

    No Known Activations