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

    Neuronpedia

    INDEX
    Explanations

    Isolation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نج
    0.46
     פ
    0.44
     গ
    0.42
     అవ
    0.41
     וח
    0.41
     prins
    0.40
     беспо
    0.40
     만
    0.39
    וני
    0.39
     прямоуго
    0.39
    POSITIVE LOGITS
     deuterium
    0.48
    ر
    0.46
    räger
    0.45
    äure
    0.45
     Nürnberg
    0.44
     Pinnacle
    0.44
    PYTHON
    0.44
     Pickett
    0.42
    subfigure
    0.42
    epub
    0.42
    Act Density 0.001%

    No Known Activations