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

    Neuronpedia

    INDEX
    Explanations

    git commit messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的影响
    0.44
     হয়েছে
    0.43
     impacted
    0.42
     geändert
    0.41
     হয়েছে
    0.40
    ilmiştir
    0.40
     ಕೈ
    0.40
     motivated
    0.39
     reviewer
    0.39
     motivates
    0.39
    POSITIVE LOGITS
    feat
    0.49
    ui
    0.45
     develop
    0.45
     ci
    0.43
    UI
    0.42
     struktur
    0.42
     estrutura
    0.42
     combat
    0.41
     styling
    0.41
     feats
    0.41
    Act Density 0.002%

    No Known Activations