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

    Neuronpedia

    INDEX
    Explanations

    concept_ and mark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     själv
    0.40
    ও
    0.40
    াসা
    0.39
    ountains
    0.39
    å
    0.39
    icks
    0.38
    usega
    0.37
    ାଇ
    0.37
    ungkinkan
    0.36
    kyat
    0.36
    POSITIVE LOGITS
     inventions
    0.41
     sug
    0.39
     invented
    0.38
     algoritmo
    0.38
     obstru
    0.38
     banner
    0.37
     अवशेष
    0.37
     Deine
    0.36
    പ്പറ
    0.36
     accompl
    0.36
    Act Density 0.001%

    No Known Activations