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

    Neuronpedia

    INDEX
    Explanations

    creates waves, identity, things affect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সুখী
    0.45
    arse
    0.43
    Seb
    0.41
    Cr
    0.40
    CU
    0.39
    Bers
    0.39
    So
    0.39
    rs
    0.38
     bers
    0.38
    Ce
    0.38
    POSITIVE LOGITS
    ocks
    0.40
     Tyr
    0.39
    慗
    0.39
     prohibit
    0.38
     tyl
    0.38
    ייש
    0.38
    ympt
    0.37
     Relationships
    0.37
     वैसा
    0.37
     احتاج
    0.37
    Act Density 0.001%

    No Known Activations