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

    Neuronpedia

    INDEX
    Explanations

    Ukrainian borscht

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Messaging
    0.41
     messaging
    0.38
    metrics
    0.37
    Messaging
    0.37
    施工
    0.36
    psin
    0.36
     dư
    0.36
    ektion
    0.36
     onboarding
    0.35
    屻
    0.35
    POSITIVE LOGITS
    ENAME
    0.45
     crack
    0.42
     ако
    0.41
    克兰
    0.41
     丿
    0.41
     اگر
    0.40
     Oppen
    0.40
     alcoholism
    0.39
    兇
    0.39
     ци
    0.39
    Act Density 0.000%

    No Known Activations