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

    Neuronpedia

    INDEX
    Explanations

    record warmest year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RENGTH
    0.41
    APPY
    0.39
     সেন
    0.38
    ATORY
    0.38
    Truth
    0.38
    Transition
    0.38
     pointwise
    0.38
     jurisprudence
    0.38
    (":
    0.36
    鮮
    0.36
    POSITIVE LOGITS
     bolsillo
    0.42
     pocket
    0.40
     scorecard
    0.40
     IMF
    0.39
     Messaging
    0.39
    ເວລາ
    0.39
     pk
    0.37
     मैसेज
    0.37
     ıs
    0.37
     plowed
    0.37
    Act Density 0.016%

    No Known Activations