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

    Neuronpedia

    INDEX
    Explanations

    concepts coming into play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bring
    0.38
     boasts
    0.34
    Bring
    0.34
    bring
    0.33
     বজ
    0.33
     bring
    0.32
     Brings
    0.32
     yy
    0.32
     patted
    0.32
     düz
    0.31
    POSITIVE LOGITS
     forefront
    0.36
     passe
    0.34
     cristall
    0.33
    ार्
    0.32
     happening
    0.30
     unexpectedly
    0.30
     flying
    0.30
     выпу
    0.29
     pass
    0.29
     Роб
    0.29
    Act Density 0.006%

    No Known Activations