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

    Neuronpedia

    INDEX
    Explanations

    NBA finals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    má
    1.04
    iguous
    0.96
    साथ
    0.95
    いない
    0.92
     få
    0.85
    ங்கிணை
    0.85
    aneous
    0.84
     lângă
    0.84
    ro
    0.84
     overlapped
    0.84
    POSITIVE LOGITS
    𝒆
    0.91
     XVIII
    0.91
     Lorentz
    0.90
     riser
    0.88
    𝒕
    0.87
     оцени
    0.85
     voltaje
    0.85
    ौन
    0.84
     finales
    0.83
     biologique
    0.83
    Act Density 0.005%

    No Known Activations