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

    Neuronpedia

    INDEX
    Explanations

    easy to remember and pronounce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بتاريخ
    0.43
     formalized
    0.43
     rigorous
    0.43
     ernst
    0.40
     enriqu
    0.39
     científica
    0.39
     systematically
    0.39
    的花
    0.39
     akademik
    0.38
     बारी
    0.38
    POSITIVE LOGITS
     memorable
    0.98
     catchy
    0.93
     easy
    0.92
     memor
    0.87
    覚え
    0.85
     mudah
    0.81
     easily
    0.80
    容易
    0.79
     kolay
    0.79
     সহজে
    0.78
    Act Density 0.015%

    No Known Activations