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

    Neuronpedia

    INDEX
    Explanations

    computing and research fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aldosterone
    0.46
    usus
    0.45
     hailed
    0.45
     nostru
    0.45
     aproximativ
    0.44
     agre
    0.44
    )=-
    0.44
     vzduchu
    0.44
     restric
    0.44
     diminue
    0.44
    POSITIVE LOGITS
    పై
    0.51
    考古
    0.46
    牯
    0.46
     Thought
    0.45
    ochem
    0.45
     Пока
    0.45
     Dokl
    0.45
     Chất
    0.44
    ের
    0.44
    ertation
    0.44
    Act Density 0.005%

    No Known Activations