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

    Neuronpedia

    INDEX
    Explanations

    input("You:")

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     traditional
    0.88
     prowess
    0.74
     aerob
    0.71
     aging
    0.70
     aut
    0.70
     end
    0.68
     mainstream
    0.66
     tops
    0.66
     pure
    0.64
     sheer
    0.64
    POSITIVE LOGITS
    Something
    1.08
    Somewhere
    1.05
    :...
    1.03
    acă
    1.02
    elihat
    1.01
    hatian
    0.99
    But
    0.98
    ፦
    0.98
    Since
    0.98
    enzen
    0.98
    Act Density 0.000%

    No Known Activations