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

    Neuronpedia

    INDEX
    Explanations

    advantages or theories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.53
     طور
    0.46
     உண
    0.44
     calme
    0.44
     повто
    0.44
     Reads
    0.44
     lưới
    0.42
     выборах
    0.42
     automaticamente
    0.42
     pertanto
    0.41
    POSITIVE LOGITS
    ыргыз
    0.48
    ساعد
    0.46
    Polynomial
    0.46
    規
    0.45
    ningarna
    0.45
    polynomial
    0.44
    導
    0.44
    Setelah
    0.44
    巴西
    0.44
     मर्यादा
    0.44
    Act Density 0.003%

    No Known Activations