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

    Neuronpedia

    INDEX
    Explanations

    concluding or qualifying phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jonka
    0.23
    scopic
    0.21
     whose
    0.21
     facteurs
    0.20
     noire
    0.20
     formas
    0.20
     আনোয়ার
    0.20
     spasms
    0.19
     noires
    0.19
     cuyo
    0.19
    POSITIVE LOGITS
     hopefully
    0.21
     помочь
    0.20
     в
    0.19
     Ultimately
    0.19
     In
    0.19
     therefore
    0.19
     conceivably
    0.19
     Thus
    0.19
     Ideally
    0.19
     in
    0.18
    Act Density 0.046%

    No Known Activations