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

    Neuronpedia

    INDEX
    Explanations

    experimental methods and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     их
    0.39
     stent
    0.38
     많
    0.38
     lately
    0.38
     Graphical
    0.38
     स्टेन
    0.37
     이동
    0.37
     Length
    0.36
     한
    0.36
    将其
    0.36
    POSITIVE LOGITS
    မှုကို
    0.33
    ाइन
    0.32
    狨
    0.32
     söyled
    0.32
    িবেন
    0.32
    barrier
    0.31
    hia
    0.31
     certify
    0.31
     equilibrium
    0.31
    ijd
    0.30
    Act Density 0.002%

    No Known Activations