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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inilah
    0.50
     geht
    0.41
     tyto
    0.40
     tuvimos
    0.40
    இந்தப்
    0.40
     tivemos
    0.39
     gemeins
    0.39
     இந்தப்
    0.38
     explique
    0.38
     go
    0.38
    POSITIVE LOGITS
    ueger
    0.48
    自身の
    0.46
     Jego
    0.43
    那边
    0.43
     свои
    0.42
    Cnt
    0.41
     Ор
    0.40
     своего
    0.40
     Walls
    0.39
     njegova
    0.38
    Act Density 0.975%

    No Known Activations