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

    Neuronpedia

    INDEX
    Explanations

    string segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rak
    0.44
    uma
    0.44
    le
    0.42
    une
    0.41
    0
    0.40
    iope
    0.39
    icker
    0.39
    era
    0.39
    opy
    0.38
    onia
    0.38
    POSITIVE LOGITS
     matemat
    0.42
     इनमें
    0.40
     Balliye
    0.40
     parcel
    0.40
     bereaved
    0.40
     അമേ
    0.39
     တစ်
    0.39
     धरो
    0.38
    帳に追加
    0.38
     practition
    0.38
    Act Density 0.001%

    No Known Activations