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

    Neuronpedia

    INDEX
    Explanations

    updates, without slowdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.45
    cl
    0.43
    瞅
    0.43
     ब्रैकेट
    0.39
    Xinhua
    0.39
    dcs
    0.38
    vány
    0.38
    utter
    0.38
     buttons
    0.38
    ilion
    0.38
    POSITIVE LOGITS
     predominance
    0.56
     corne
    0.55
     tradiciones
    0.51
    おい
    0.49
     predominant
    0.48
     kese
    0.47
     oce
    0.46
     uș
    0.45
     rupture
    0.45
     supersede
    0.44
    Act Density 0.003%

    No Known Activations