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

    Neuronpedia

    INDEX
    Explanations

    introduces capabilities or specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スル
    0.41
     Dic
    0.40
    েন্দ্র
    0.39
     Меди
    0.38
    хара
    0.38
     江
    0.37
     whims
    0.37
    рис
    0.37
     حاض
    0.36
    ধি
    0.35
    POSITIVE LOGITS
    曬
    0.42
    딨
    0.42
     alarma
    0.41
    ₂,
    0.41
    VSLU
    0.38
     pérd
    0.38
     jurnal
    0.38
     Jodie
    0.38
    hardt
    0.38
     lavoro
    0.38
    Act Density 0.000%

    No Known Activations