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

    Neuronpedia

    INDEX
    Explanations

    steps or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     człowieka
    0.41
     proteína
    0.38
     partícula
    0.38
     secondNumber
    0.38
    జాగా
    0.38
     édition
    0.38
     molécule
    0.37
     periodista
    0.37
     entusi
    0.37
    zący
    0.37
    POSITIVE LOGITS
     Goals
    0.40
     इनका
    0.39
     их
    0.38
     denen
    0.38
     kanilang
    0.38
    ßerdem
    0.38
     jeweils
    0.38
     इनके
    0.38
     Conclusion
    0.37
     niiden
    0.37
    Act Density 0.100%

    No Known Activations