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

    Neuronpedia

    INDEX
    Explanations

    Multi-AZ deployments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وذ
    0.40
     따른
    0.38
    emann
    0.37
    ляются
    0.37
    υχ
    0.37
     pezzi
    0.36
     voorkomen
    0.36
     યાદ
    0.36
    луу
    0.36
     costes
    0.36
    POSITIVE LOGITS
    Words
    0.41
    show
    0.40
    Σ
    0.39
     Words
    0.39
    আমাদের
    0.38
    כו
    0.38
    continues
    0.38
     appropriate
    0.38
    complex
    0.38
     CONTINUE
    0.38
    Act Density 0.000%

    No Known Activations