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

    Neuronpedia

    INDEX
    Explanations

    iterating and refining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पैदा
    0.36
     بنابراین
    0.35
     creates
    0.35
     terminates
    0.35
     需要
    0.33
     becomes
    0.33
    creates
    0.32
    говари
    0.32
    であるが
    0.32
     became
    0.31
    POSITIVE LOGITS
    out
    0.39
    then
    0.35
    hope
    0.35
    ou
    0.34
    FORD
    0.34
    retail
    0.33
    in
    0.32
    cha
    0.32
    forced
    0.32
    ford
    0.32
    Act Density 0.047%

    No Known Activations