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

    Neuronpedia

    INDEX
    Explanations

    2nd and 3rd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    th
    1.03
    ướ
    0.89
    ্বস্ত
    0.86
     myosin
    0.83
     variety
    0.79
    waypoints
    0.79
    AnimationClip
    0.78
     habitual
    0.77
     Bewert
    0.77
    ização
    0.76
    POSITIVE LOGITS
    nd
    3.75
     nd
    2.62
    ND
    2.57
    nds
    2.12
    Nd
    2.08
    thirds
    1.81
     thirds
    1.77
    ndi
    1.76
     ND
    1.76
    ndan
    1.55
    Act Density 0.483%

    No Known Activations