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

    Neuronpedia

    INDEX
    Explanations

    solving equations for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stor
    0.40
     trei
    0.39
    manager
    0.38
     cannot
    0.38
    you
    0.38
    mutex
    0.38
    task
    0.37
     encourages
    0.37
    ِين
    0.37
    psych
    0.37
    POSITIVE LOGITS
     сейчас
    0.41
     ప్రస్తు
    0.41
     ఇప్పుడు
    0.40
     আসে
    0.39
    现在
    0.39
     ঘটছে
    0.39
    同じ
    0.38
     моего
    0.38
     আহমে
    0.38
     தற்போது
    0.38
    Act Density 0.001%

    No Known Activations