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

    Neuronpedia

    INDEX
    Explanations

    search, scroll, choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conduits
    0.45
     jamais
    0.45
     mysticism
    0.42
     nedir
    0.42
     benign
    0.41
     homeostasis
    0.41
     hogares
    0.41
     legality
    0.41
     sterility
    0.41
     entail
    0.40
    POSITIVE LOGITS
     search
    1.00
    search
    0.94
    scroll
    0.93
     يمكنك
    0.93
     Search
    0.92
     choose
    0.90
     scroll
    0.90
    你可以
    0.89
     Choose
    0.88
     Scroll
    0.88
    Act Density 0.013%

    No Known Activations