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

    Neuronpedia

    INDEX
    Explanations

    trading decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starred
    0.36
     ખાતે
    0.35
     തന്നെയാണ്
    0.33
     installed
    0.32
     Zentr
    0.32
    pmod
    0.31
    nen
    0.31
    ≃
    0.31
     Bộ
    0.31
    हतक
    0.31
    POSITIVE LOGITS
    goers
    0.37
     maladies
    0.35
    ьев
    0.34
     animales
    0.33
     разви
    0.32
    ער
    0.32
    <unused2008>
    0.32
     문제를
    0.31
     ਦਿ
    0.31
     ሕ
    0.31
    Act Density 0.447%

    No Known Activations