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

    Neuronpedia

    INDEX
    Explanations

    prominently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lni
    0.46
     śnie
    0.43
    ServiceName
    0.42
    Service
    0.41
    weile
    0.41
    SERVICE
    0.40
     సామ
    0.40
     SERVICE
    0.40
    ową
    0.39
    䣰
    0.39
    POSITIVE LOGITS
     ver
    0.39
     length
    0.37
     dinheiro
    0.36
    接地
    0.35
     overw
    0.34
    ver
    0.34
     Placing
    0.34
     fits
    0.33
     nad
    0.33
     Length
    0.33
    Act Density 0.001%

    No Known Activations