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

    Neuronpedia

    INDEX
    Explanations

    body weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     goû
    1.07
     Vacuum
    1.03
     Saturn
    1.02
     H
    1.00
     Yellowstone
    1.00
    upper
    1.00
    ር
    1.00
     Moon
    0.99
     Klam
    0.99
    по
    0.98
    POSITIVE LOGITS
    eniem
    1.06
    ঙালি
    1.01
    indazole
    1.00
     saddo
    0.98
    emap
    0.98
     camisetas
    0.98
    🠀
    0.98
    ないと
    0.98
    isetas
    0.98
    屽
    0.97
    Act Density 0.001%

    No Known Activations