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

    Neuronpedia

    INDEX
    Explanations

    evaluating properties and effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bagaimana
    0.54
    ura
    0.53
     Почему
    0.51
     Jangan
    0.50
     Кто
    0.50
     Tidak
    0.49
     Apakah
    0.49
    omio
    0.49
    hi
    0.49
     Какие
    0.49
    POSITIVE LOGITS
     scalars
    0.59
     axles
    0.54
     graphene
    0.53
     centroids
    0.53
     destabil
    0.53
     overwhelm
    0.52
     luminosity
    0.51
     photons
    0.51
     fermion
    0.51
     chronically
    0.51
    Act Density 0.001%

    No Known Activations