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

    Neuronpedia

    INDEX
    Explanations

    documentation access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nationen
    0.48
     subjects
    0.41
     discipline
    0.40
     domain
    0.39
     ejercicios
    0.39
     Subjects
    0.39
    iker
    0.39
    ordinated
    0.38
     प्रारूप
    0.38
     format
    0.38
    POSITIVE LOGITS
    ią
    0.41
     আমির
    0.40
    odb
    0.40
     Cela
    0.40
    rors
    0.39
     ощущение
    0.39
    口碑
    0.38
     expliquer
    0.38
     возник
    0.38
    rots
    0.37
    Act Density 0.000%

    No Known Activations