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

    Neuronpedia

    INDEX
    Explanations

    algorithm and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sărb
    0.64
     anuncia
    0.61
     cidade
    0.61
    maması
    0.61
    funcionario
    0.60
    权力
    0.59
     herkes
    0.59
    上涨
    0.59
    isAuthenticated
    0.58
     मेहमान
    0.57
    POSITIVE LOGITS
     algorithms
    1.35
     algorithm
    1.33
     method
    1.19
     methods
    1.19
    算法
    1.16
     Algorithm
    1.16
     techniques
    1.14
     алгорит
    1.13
    Algorithm
    1.13
     algorit
    1.12
    Act Density 0.422%

    No Known Activations