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

    Neuronpedia

    INDEX
    Explanations

    copy and paste instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    住了
    0.40
     anatomy
    0.39
     Bunker
    0.38
    頂きました
    0.38
     hill
    0.37
    দানে
    0.37
    স্তি
    0.37
     এমনই
    0.37
    هما
    0.37
     erbjud
    0.37
    POSITIVE LOGITS
    copy
    0.47
    lp
    0.39
    2
    0.39
     Copy
    0.38
    bc
    0.38
    }/{
    0.38
    using
    0.38
    z
    0.38
    Copy
    0.38
    osy
    0.38
    Act Density 0.005%

    No Known Activations