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

    Neuronpedia

    INDEX
    Explanations

    invest in or invest heavily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੀ
    3.29
    ne
    3.08
    री
    3.03
    te
    2.79
    ◍
    2.73
    此之外
    2.73
    för
    2.69
    й
    2.63
    রা
    2.62
    зать
    2.57
    POSITIVE LOGITS
    л
    3.79
    ב
    3.25
    ва
    3.07
    u
    3.01
    ein
    2.88
    eurs
    2.86
    ق
    2.85
    ä
    2.78
     heavily
    2.63
     libid
    2.55
    Act Density 0.033%

    No Known Activations