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

    Neuronpedia

    INDEX
    Explanations

    technical and multilingual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     できる
    0.43
    不但
    0.39
     OL
    0.36
     LAD
    0.36
    DataXYZ
    0.36
    どんどん
    0.36
     hybrid
    0.35
     tessuto
    0.35
     FAST
    0.35
     называется
    0.35
    POSITIVE LOGITS
    7
    0.39
    好
    0.37
    物
    0.36
    μένου
    0.36
     আহমে
    0.35
     responsables
    0.35
     पीड़िता
    0.35
    関連
    0.35
    とその
    0.34
    め
    0.34
    Act Density 0.047%

    No Known Activations