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

    Neuronpedia

    INDEX
    Explanations

    address, finger, or feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permittivity
    1.06
    Dense
    1.05
    িপ্ত
    1.02
    hidupan
    1.02
    ก่อ
    0.99
     Acest
    0.98
     ateş
    0.96
    unu
    0.96
    kerja
    0.96
    ট্ট
    0.96
    POSITIVE LOGITS
     scraps
    1.05
     semblance
    0.99
     alma
    0.98
    可
    0.94
    seat
    0.94
    st
    0.92
     genes
    0.92
     achievable
    0.90
     δυνατό
    0.90
     wur
    0.90
    Act Density 0.001%

    No Known Activations